Open-weight models and local runtimes released in the last 30 days · updated 2026-10-24T23:23:29Z
Filters
Runs on (pick one or more)
Any device
Params (total)
to
My lab
Models 185
kindlingai/glm-5.3-exlr8-k2-k3-k4 2026-10-08 EXLR8 is a new quantization format. Mixture-of-experts (256 experts, 8 per token). Context: 1M tokens (config). License: glm-5.3. Vendor-reported: "GLM-5.3's top-8 routing turns small numeric differences into different experts: two BF16 run
MiniMaxAI/MiniMax-M3.1-Flash 2026-10-17 MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. Mixture-of-experts, 220B total, 23B active (128 experts, 4 per token). Context: 1M tokens (config). License: Runs on: need Q4 134.3 GB / Q8 261.1 GB / FP16 443.0 GB; smallest fit Q4: 2× DGX Spark (256GB), Q8: Mac 512GB
kindlingai/glm-5.3-flash-exlr8-k2-k3-k4 2026-10-14 GLM-5.3-Flash is a MoE model: 45 layers (0-2 dense, 3-44 MoE), 288 routed experts with top-8 routing plus one shared expert per MoE layer, an MTP layer 45 and a vision tower. Mixture-of-experts (288 experts, 8 per token). Context: 1M tokens
LiconStudio/Minimax-H3-VBVR 2026-10-23 Licon VBVR is an image-to-video LoRA for MiniMax-H3, trained on VBVR data rebuilt and reprocessed specifically for H3. License: apache-2.0.
tencent/WeVisOne-VL-4B 2026-10-22 WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Dense, 4.8B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 4.9 GB / Q8 7.4 GB / FP16 11.9 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
HuggingFaceBio/Carbon-X 2026-10-21 Carbon-X is a 14.8B-parameter decoder-only language model trained jointly on DNA sequences and natural-language text. Dense, 15B params. Context: 40K tokens (config). License: apache-2.0. Runs on: need Q4 11.9 GB / Q8 18.1 GB / FP16 32.0 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
RBDash-Team/Xing-VL1.0-Decision 2026-10-22 Xing-VL1.0-Decision is a 27B multimodal typed decision model. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 19.6 GB / Q8 32.3 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
tencent/WeVisOne-VL-2B 2026-10-22 WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Dense, 2.4B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 3.2 GB / Q8 4.5 GB / FP16 6.8 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
sky7350/Mica-v0.5-4B 2026-09-27 Mica is a 4B model that answers your questions about an input with a probability for every answer you allow. Dense, 4.7B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 4.9 GB / Q8 7.1 GB / FP16 11.4 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
bottlecapai/ThinkingCap-Qwen3.8-Flash-Next 2026-10-22 Thinking is on at reasoningeffort=xhigh, the chat template's own default, with the base model's recommended sampling — temperature=1.0, topp=0.95, topk=20, minp=0.0 — used unchanged for Ours. Mixture-of-experts, 180B total (512 Runs on: need Q4 115.0 GB / Q8 192.8 GB / FP16 361.0 GB; smallest fit Q4: 1× DGX Spark (128GB), Q8: 2× DGX Spark (256GB), FP16: Mac 512GB
MinimaLabs/KLM-1.5 2026-10-22 KLM 1.5 is a 99M-parameter base language model. Dense, 99M params. Context: 2K tokens (config). License: apache-2.0. Runs on: need Q4 1.3 GB / Q8 1.3 GB / FP16 1.4 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 2026-10-05 NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 is a small language model (SLM) further post-trained from Gemma-4-E4B-it by NVIDIA. Dense, 8B params. Context: 64K tokens (config). License: openmdw-1.1. Runs on: need Q4 6.8 GB / Q8 9.9 GB / FP16 16.8 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
inclusionAI/Ling-3.0-flash-Sante 2026-10-19 Text generation model from inclusionAI (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 127B total, 5.1B active (512 experts, 8 per token). Context: 256K tokens (config). License: mit. Runs on: need Q4 77.9 GB / Q8 137.8 GB / FP16 256.4 GB; smallest fit Q4: 96GB GPU (RTX Pro 6000 Blackwell), Q8: 2× DGX Spark (256GB), FP16: Mac 512GB
fastino/GLiDE 2026-10-19 GLiDE is a decision model from Fastino. Dense, 26B params. Context: 256K tokens (config). License: fastino-community. Runs on: need Q4 18.8 GB / Q8 30.8 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
ltzheng/Qwen3.5-9B-General-Game-Stage1-3Shift-Shuffled 2026-10-22 Image text to text model from ltzheng (HF pipeline tag; the card has no one-line description). Dense, 9.7B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 7.9 GB / Q8 12.4 GB / FP16 21.4 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), FP16: 24GB GPU (3090 / 4090)
darkc0de/XORTRON-AgentRICO 2026-10-19 XORTRON is an experimental research system. Dense, 28B params. Context: 256K tokens (config). Runs on: need Q4 19.9 GB / Q8 32.8 GB / FP16 57.8 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
som-doe2007/geoai-outdoor-assistant 2026-10-23 Text generation model from som-doe2007 (HF pipeline tag; the card has no one-line description). License: apache-2.0.
bottlecapai/ThinkingCap-gemma-4-26B-A4B-it 2026-10-23 Image text to text model from bottlecapai (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 20.0 GB / Q8 29.9 GB / FP16 53.5 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
NorviTech/armiger-ultra 2026-10-18 Armiger Ultra is a 9-head byte-level RoPE Transformer (d=256, 6 layers, 8 heads) with a 6-plugin pipeline for raw BitTorrent/DHT metadata (name, file-tree paths + sizes, optional tracker/DHT counters). License: apache-2.0.
Hikari07jp/DeepSeek-V4.1-1017-Ablitrated-testmodel 2026-10-23 Image text to text model from Hikari07jp (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 763B total (384 experts, 6 per token). Context: 1M tokens (config). License: mit. Vendor-reported: "Hidden size 5120, voca Runs on: need Q4 459.6 GB / Q8 812.6 GB / FP16 1528.1 GB
tattrongvu/Jeffan-31b-1710 2026-10-19 Text classification model from tattrongvu (HF pipeline tag; the card has no one-line description). Dense, 31B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "The Decision Index runs use the engine in inference/ Runs on: need Q4 27.8 GB / Q8 42.5 GB / FP16 71.6 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
Valen-Team/Valen-0.8B 2026-10-05 Image text to text model from Valen-Team (HF pipeline tag; the card has no one-line description). Dense, 854M params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 1.9 GB / Q8 2.3 GB / FP16 3.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/InternVideo2-CLIP-anomaly-detection 2026-10-22 Input Parameters: Video is a temporal sequence of two-dimensional RGB frames; text is a one-dimensional token sequence. 373M params. License: nvidia-internal-scientific-research-and-development-model-license. Vendor-reported: "The fine-tune Runs on: need Q4 1.7 GB / Q8 1.9 GB / FP16 2.2 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
ufakai/ufakzeka-kulak 2026-10-22 ufakzeka-kulak ("kulak" is Turkish for ear) is a small Turkish speech-to-text model by ufak AI, trained from scratch and released under Apache-2.0. License: apache-2.0.
kakaocorp/kanana-2-vision-encoder-medium 2026-10-12 Kanana-2-vision-encoder is Kakao's vision encoder series for vision-language models. Dense, 427M params. License: kanana-open-license. Runs on: need Q4 2.2 GB / Q8 2.4 GB / FP16 2.8 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
internlm/Atria-Dawn 2026-10-23 Atria Dawn is a new-generation agentic model developed by the Shanghai Artificial Intelligence Laboratory. Mixture-of-experts, 753B total (256 experts, 8 per token). Context: 1M tokens (config). Runs on: need Q4 453.7 GB / Q8 802.1 GB / FP16 1508.4 GB
nvidia/GR00T-N1.7-AppleToPlate-cosine40k-checkpoint-15000 2026-10-13 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 3.1B params. Runs on: need Q4 3.4 GB / Q8 4.8 GB / FP16 7.8 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
ccortezb/FinOptix-14B-v2 2026-10-23 FinOptix-14B v2 is an open-weights FinOps specialist fine-tuned on Qwen 2.5 14B Instruct. Dense, 15B params. Context: 32K tokens (config). License: apache-2.0. Runs on: need Q4 11.6 GB / Q8 18.3 GB / FP16 32.1 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
GrootTeam/Groot-19B-A3B-261023 2026-10-23 Groot is a family of open-weight reasoning models for complex real-world tasks. Mixture-of-experts, 19B total, 3B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "Groot-19B-A3B-261023 Runs on: need Q4 13.4 GB / Q8 22.5 GB / FP16 40.6 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
SubMaroon/Kitchoon-V3-26B-A4B 2026-10-20 The Kitchoon series is designed as an RP- and ERP-oriented model, focusing on character development and featuring a neutral writing style. Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). L Runs on: need Q4 19.8 GB / Q8 29.9 GB / FP16 54.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
bayliner1980/Qwen3-0.6B-MoE-A0.5B 2026-10-23 Text generation model from bayliner1980 (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 597M total, 500M active (32 experts, 16 per token). Context: 40K tokens (config). License: apache-2.0. Vendor-reported: "At Runs on: need Q4 2.3 GB / Q8 2.5 GB / FP16 3.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
incoai/MiniMax-M3.1-Flash-DFlash2 2026-10-19 DFlash 2 is a block-diffusion drafter for speculative decoding. Dense, 2.1B params. Context: 1M tokens (config). License: apache-2.0. Runs on: need Q4 2.5 GB / Q8 3.5 GB / FP16 5.4 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
ReadyArt/Wicked-Stuff-26B-A4B-v2.0-Final 2026-10-23 Text generation model from ReadyArt (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 19.8 GB / Q8 29.9 GB / FP16 54.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
berryber09/FastH3-OmniRef-8step-pruned-w4a8 2026-10-23 Text to video model from berryber09 (HF pipeline tag; the card has no one-line description). License: minimax-h3-community-license.
GreenBitAI/Ternary-Bonsai-2-27B-gbx 2026-10-20 Bonsai 2 ships without a draft model; this head starts from the multi-token prediction head of Qwen3.8-27B, which Bonsai 2 is built from, and is distilled on text generated by Bonsai 2 itself -- prose, code, chat and coding-agent sessions. Runs on: need Q4 19.5 GB / Q8 32.2 GB / FP16 57.8 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
Phase-Technologies/Densy-330M-Chat 2026-10-23 Densy-330M-Chat is an open-source, pure dense causal transformer language model designed and trained from scratch by Phase Technologies. 487M params. License: apache-2.0. Runs on: need Q4 1.8 GB / Q8 2.0 GB / FP16 2.5 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
owensong/Inflect-Mini-v3-Preview 2026-10-23 Text to speech model from owensong (HF pipeline tag; the card has no one-line description).
tencent/Hy-Nomas 2026-10-21 Hy-Nomas is a video world generation model that supports free-form, multi-turn interaction through text instructions and camera control. License: apache-2.0.
DavidAU/Qwen3.8-31B-Looping-Transformer 2026-10-23 Image text to text model from DavidAU (HF pipeline tag; the card has no one-line description). 31B params. License: apache-2.0. Runs on: need Q4 22.1 GB / Q8 36.4 GB / FP16 65.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
ReadyArt/Wicked-Stuff-31B-Final 2026-10-23 Text generation model from ReadyArt (HF pipeline tag; the card has no one-line description). Dense, 31B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 28.5 GB / Q8 43.1 GB / FP16 71.6 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
mingqiancha233/Socrates-Image-1.0-31B 2026-10-22 Socrates-Image-1.0 is a self-contained dense text-to-image model with recurrent visual-semantic feedback. 31B params. License: qwen-research. Runs on: need Q4 22.2 GB / Q8 36.5 GB / FP16 65.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
tencent/Hy-Nomas-Diffusers 2026-10-24 Hy-Nomas is a video world generation model that supports free-form, multi-turn interaction through text instructions and camera control. 8.6B params. License: apache-2.0. Runs on: need Q4 6.8 GB / Q8 10.8 GB / FP16 18.8 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
BlueRoseLabs/Silencio 2026-10-23 Silencio is built on two open models. 34M params. License: apache-2.0. Runs on: need Q4 1.5 GB / Q8 1.5 GB / FP16 1.6 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
ReadyArt/Omega-Arsenal-26B-A4B-Final 2026-10-22 Text generation model from ReadyArt (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 20.7 GB / Q8 30.6 GB / FP16 54.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
h2oai/timeh2o-v1 2026-10-22 Time series foundation model by H2O.ai. 109M params. License: h2o-model-non-commercial-licence-v1.0. Runs on: need Q4 1.6 GB / Q8 1.6 GB / FP16 1.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
DavidAU/Qwen3.8-40B-Ultimate 2026-10-22 Image text to text model from DavidAU (HF pipeline tag; the card has no one-line description). 40B params. License: apache-2.0. Runs on: need Q4 28.4 GB / Q8 46.9 GB / FP16 84.3 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
ATH-MaaS/PixText 2026-10-22 Use models/PixText-Teacher to load Teacher. License: apache-2.0.
ReadyArt/Wicked-Stuff-26B-A4B-v2.1-FINAL 2026-10-24 Text generation model from ReadyArt (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 26B total, 4B active (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 18.5 GB / Q8 29.9 GB / FP16 54.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
hi3d-official/Hi3Dv1.0 2026-10-16 Image to 3d model from hi3d-official (HF pipeline tag; the card has no one-line description). License: hi3d-open-license-agreement-1.0.
nikopueringer/CorridorKey2.0 2026-10-13 CorridorKey runs on features from three frozen foundation models. License: corridor-key-licence-2.0.
AnveshAI/AnveshAI-CoderLM-0.1B 2026-10-22 CoderLM is a compact 100.2M-parameter language model purpose-built for multi-language code generation across 13 programming and markup languages — Python, Java, JavaScript, C++, C, Rust, TypeScript, Go, HTML, CSS, Shell, SQL, and Markdown. Runs on: need Q4 1.2 GB / Q8 1.2 GB / FP16 1.3 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
turion-ai/turion-jev-31b 2026-10-22 Turion Jev 31B is a decision model by Turion AI, fine-tuned from google/gemma-4-31B-it on the Turion AI model training platform. Dense, 31B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 27.9 GB / Q8 42.3 GB / FP16 71.6 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
RecursiveSI/flint 2026-10-21 Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. Mixture-of-experts, 40B total (256 experts, 6 per token). Context: 256K tokens (con Runs on: need Q4 26.9 GB / Q8 44.1 GB / FP16 81.4 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
KRAFTON/Raon-1-mini-preview 2026-10-21 Raon-1 mini is a 30B-A4B Mixture-of-Experts (MoE) language model, designed and trained from scratch by KRAFTON AI. Mixture-of-experts, 29B total (128 experts, 6 per token). Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 20.9 GB / Q8 32.6 GB / FP16 58.8 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
inclusionAI/Ling-3.0-tiny-UBTree 2026-10-21 Text generation model from inclusionAI (HF pipeline tag; the card has no one-line description). Dense, 183M params. Context: 128K tokens (config). License: mit. Runs on: need Q4 1.4 GB / Q8 1.5 GB / FP16 1.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
FastVideo/FastH3-Omni-Comfy 2026-10-20 FastH3 Omni was built in close collaboration with Nuva Lab, which co-developed the model with FastVideo, defined and curated the omni reference dataset, and brought production-grounded creative video workflows to FastH3. License: minimax-h3 Runs on: need Q4 14.7 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
XHToken/Spark-X2.6-4B 2026-10-19 Search for "Spark-X2.6" in LM Studio and download the model. Dense, 4.1B params. Context: 1M tokens (config). License: apache-2.0. Vendor-reported: "They achieve state-of-the-art performance among similarly sized open-source models, matchin Runs on: need Q4 5.7 GB / Q8 6.6 GB / FP16 10.4 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
lodestones/Kromoss 2026-10-19 Kromoss is a full fine-tune of MOSS-Image-Base at 1024 px. 5.1B params. License: apache-2.0. Runs on: need Q4 5.1 GB / Q8 7.2 GB / FP16 11.7 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
briaai/Fibo-2.0-edit-turbo 2026-10-19 Fibo 2.0 is the of Bria's FIBO family. 8.1B params. License: bria-fibo. Runs on: need Q4 6.6 GB / Q8 10.3 GB / FP16 18.0 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
gradium/phonon-31m-en 2026-10-19 phonon-31m is a text-to-speech model from the Phonon family. Dense, 41M params. Context: 8K tokens (config). License: apache-2.0. Runs on: need Q4 1.1 GB / Q8 1.1 GB / FP16 1.2 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
vllm-sr/d3-turbo 2026-10-19 d3-turbo is the upgraded 27B multimodal decision model of Decision 3.0, the decision models of vLLM Semantic Router. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 18.8 GB / Q8 30.8 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
gradium/phonon-40m-en 2026-10-19 phonon-40m is a text-to-speech model from the Phonon family. 51M params. License: cc-by-nc-4.0. Runs on: need Q4 1.5 GB / Q8 1.6 GB / FP16 1.6 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Cosmos3-H-Dreams 2026-10-19 Cosmos3-H-Dreams is the successor of Cosmos-H-Dreams (arXiv:2608.24199), which was based on Cosmos-Predict2.5. License: nvidia-open-model-license.
LiquidAI/LFM2.5-24B-A2B-DSpark 2026-10-19 LFM2.5-24B-A2B-DSpark is a speculative-decoding draft model for LiquidAI/LFM2.5-24B-A2B. Dense, 328M params. Context: 128K tokens (config). License: lfm1.0. Runs on: need Q4 1.3 GB / Q8 1.4 GB / FP16 1.8 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Cosmos3-H-Embodied-Nano 2026-10-19 Cosmos3-H-Embodied-Nano is the successor of Cosmos-H-Surgical-Simulator, which was a forward-dynamics-only surgical simulator built on the 2B-parameter Cosmos-Predict2.5 diffusion transformer. License: nvidia-open-model-license.
nvidia/cosmos3-nano-libero10-sdg-export-S2_s43 2026-10-19 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
nvidia/cosmos3-nano-libero10-sdg-export-S5_2_s43 2026-10-19 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
nvidia/cosmos3-nano-libero10-sdg-export-D2_s43 2026-10-19 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
briaai/Fibo-2.0-dev 2026-10-18 Fibo 2.0 is the of Bria's FIBO family. 8.1B params. License: bria-fibo. Runs on: need Q4 6.6 GB / Q8 10.3 GB / FP16 18.0 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
deepseek-ai/DeepSeek-V4.1-Flash-1017 2026-10-17 DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Mixture-of-experts, 763B total (384 experts, 6 per token). Context: 1M to Runs on: need Q4 502.4 GB / Q8 510.1 GB / FP16 1528.1 GB
autotrust/AutoTrust-JEV-27B-v1.1 2026-10-17 AutoTrust-JEV-27B v1.1 is a text decision model that assigns probabilities to the answer options supplied with each question. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 19.5 GB / Q8 32.2 GB / FP16 57.8 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
microsoft/Sentiment-Analysis-7B 2026-10-17 Sentiment-Analysis-7B is a 7B-parameter autoregressive language model fine-tuned for sentiment classification of user messages directed at a service, product, or agent (the "Target"). Dense, 7.2B params. Context: 32K tokens (config). Licens Runs on: need Q4 6.5 GB / Q8 9.8 GB / FP16 16.6 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
lodestones/MOSS-Image-SFT-8-steps-dmd 2026-10-16 5.1B params. License: apache-2.0. Runs on: need Q4 4.5 GB / Q8 6.9 GB / FP16 11.7 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 2026-10-16 NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 is a looped (latent-recurrent) large language model (LLM) trained by NVIDIA. Dense, 4B params. Context: 256K tokens (config). License: openmdw-1.1. Runs on: need Q4 6.3 GB / Q8 7.6 GB / FP16 11.4 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
ornith-ai/Ornith-1.5-122B 2026-10-16 Text generation model from ornith-ai (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 125B total (256 experts, 8 per token). Context: 256K tokens (config). License: mit. Runs on: need Q4 77.6 GB / Q8 134.4 GB / FP16 251.2 GB; smallest fit Q4: 96GB GPU (RTX Pro 6000 Blackwell), Q8: 2× DGX Spark (256GB), FP16: Mac 512GB
tencent/Qwen3-8B-DSpine-b16 2026-10-16 DSpine is a parallel drafter for speculative decoding. Dense, 1.2B params. Context: 40K tokens (config). License: apache-2.0. Runs on: need Q4 1.9 GB / Q8 2.5 GB / FP16 3.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Muse-Spark-Open-816B-A42B-DFlash2 2026-10-16 Image text to text model from nvidia (HF pipeline tag; the card has no one-line description). Dense, 4.4B params. Context: 1M tokens (config). License: nvidia-open-model-agreement-license. Runs on: need Q4 3.8 GB / Q8 5.9 GB / FP16 10.0 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
tencent/Hy-Memory-30B-A3B 2026-10-15 Hy-Memory-30B-A3B is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks. Mixture-of-experts, 30B total, 3B active (128 experts, 8 per toke Runs on: need Q4 20.0 GB / Q8 33.8 GB / FP16 61.9 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
InternScience/Sage-A1.5 2026-10-15 Sage‑A1.5 is a 35B Mixture‑of‑Experts agentic model based on Qwen3.6 and Agents-A1 from Shanghai AI Laboratory, built to advance long-horizon scientific problem solving through adaptive capability composition. Mixture-of-experts, 36B total Runs on: need Q4 23.4 GB / Q8 39.5 GB / FP16 72.8 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
perplexity-ai/pplx-decider-v1.2 2026-10-15 pplx-decider-v1.2 is the next version of our pplx-decider-v1.1-27b decision model, on the same Qwen3.8-27B backbone. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 18.8 GB / Q8 30.8 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
nvidia/Nemotron-3.5-Rerank-8B-BF16 2026-10-15 Text ranking model from nvidia (HF pipeline tag; the card has no one-line description). Dense, 8.4B params. Context: 256K tokens (config). License: openmdw-1.1. Vendor-reported: "Nemotron-3.5-Rerank-8B-BF16 achieves state-of-the-art results Runs on: need Q4 7.1 GB / Q8 11.0 GB / FP16 18.9 GB; smallest fit Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
perplexity-ai/pplx-decider-flash-v1.2 2026-10-15 pplx-decider-flash-v1.2 is the small version of pplx-decider-v1.2: the same joint request format, the same API and the same text and image support, at about one seventh of the size. Dense, 4.5B params. Context: 256K tokens (config). License Runs on: need Q4 4.8 GB / Q8 7.3 GB / FP16 11.2 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
nvidia/RFD4-Proteina-Diffusers 2026-10-15 Use the model for computational biomolecular design and follow designs with appropriate structural and experimental evaluation. 178M params. License: bsd-3-clause. Runs on: need Q4 1.6 GB / Q8 1.7 GB / FP16 1.9 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
black-forest-labs/flux-3-image-klein-comfy 2026-10-14 FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. License: flux-kommunity-license. Runs on: need Q4 8.8 GB / Q8 14.1 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
mistralai/Timestral-209M 2026-10-14 Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. 209M params. License: other. Runs on: need Q4 1.6 GB / Q8 1.7 GB / FP16 1.9 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
mistralai/Timestral-5M 2026-10-14 Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. 5M params. License: other. Vendor-reported: "All Timestreal models outperform every other model at th Runs on: need Q4 1.5 GB / Q8 1.5 GB / FP16 1.5 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
black-forest-labs/flux-3-image-klein-pup 2026-10-14 FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. Dense, 9.4B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 7.7 GB / Q8 11.6 GB / FP16 20.0 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), FP16: 24GB GPU (3090 / 4090)
ibm-granite/granite-switch-4.1-8b 2026-10-14 Granite Switch 4.1 8B is a modular LLM that composes a base model, multiple adapters and an encoder together so that a single hosted endpoint can move between natural-language responses, general and specialized decisions, and speech-to-text Runs on: need Q4 8.8 GB / Q8 12.5 GB / FP16 20.4 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), FP16: 24GB GPU (3090 / 4090)
inclusionAI/Ming-3.0-asr-tiny 2026-10-14 Automatic speech recognition model from inclusionAI (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 8.9B total (128 experts, 8 per token). Context: 8K tokens (config). License: mit. Runs on: need Q4 6.5 GB / Q8 10.6 GB / FP16 18.9 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
mistralai/Timestral-123M 2026-10-14 Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. 123M params. License: other. Vendor-reported: "All Timestreal models outperform every other model at Runs on: need Q4 1.6 GB / Q8 1.6 GB / FP16 1.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
mistralai/Timestral-28M 2026-10-14 Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. 28M params. License: other. Vendor-reported: "All Timestreal models outperform every other model at t Runs on: need Q4 1.5 GB / Q8 1.5 GB / FP16 1.6 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
ibm-granite/granite-switch-4.1-30b 2026-10-14 Granite Switch 4.1 30B is a modular LLM that composes a base model, multiple adapters and an encoder together so that a single hosted endpoint can move between natural-language responses, general and specialized decisions, and speech-to-tex Runs on: need Q4 24.2 GB / Q8 37.2 GB / FP16 64.3 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
microsoft/UserRepGen-4B 2026-10-14 UserRepGen-4B is a fine-tuned Qwen3.5-4B language model that generates a structured, natural-language user representation from a multi-turn user-assistant conversation. Dense, 4.5B params. Context: 256K tokens (config). License: mit. Runs on: need Q4 4.8 GB / Q8 6.6 GB / FP16 10.5 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
inclusionAI/Ling-3.0-flash-UBTree 2026-10-14 Text generation model from inclusionAI (HF pipeline tag; the card has no one-line description). Dense, 482M params. Context: 128K tokens (config). License: mit. Runs on: need Q4 2.0 GB / Q8 2.2 GB / FP16 2.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
amazon/LAR-27B 2026-10-14 Dense, 27B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 19.6 GB / Q8 31.7 GB / FP16 56.9 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
amazon/LAR-9B 2026-10-14 Dense, 9B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 7.7 GB / Q8 11.6 GB / FP16 20.0 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), FP16: 24GB GPU (3090 / 4090)
black-forest-labs/flux-3-image-klein 2026-10-13 FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. 5.5B params. License: flux-kommunity-license. Runs on: need Q4 5.2 GB / Q8 7.6 GB / FP16 12.6 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
black-forest-labs/flux-3-image-klein-base 2026-10-13 FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. 5.5B params. License: flux-kommunity-license. Runs on: need Q4 5.1 GB / Q8 7.6 GB / FP16 12.6 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
inclusionAI/Ling-3.1-flash 2026-10-13 Text generation model from inclusionAI (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 572B total (512 experts, 8 per token). Context: 256K tokens (config). License: mit. Runs on: need Q4 359.7 GB / Q8 610.1 GB / FP16 1145.9 GB; smallest fit Q4: Mac 512GB
reflection/Beam-1.0-501B-A23B-DFlash2 2026-10-13 DFlash2 draft model for Beam. Dense, 1.9B params. Context: 1M tokens (config). License: apache-2.0. Runs on: need Q4 2.4 GB / Q8 3.2 GB / FP16 5.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Kimodo-SOMA-RP-ArdyRep-v1.2 2026-10-13 The Kimodo model family includes models trained on different skeletons and datasets: Kimodo-SOMA-RP Trained on the 30-joint SOMA skeleton with the proprietary Bones Rigplay dataset. 283M params. License: nvidia-open-model-license. Runs on: need Q4 1.7 GB / Q8 1.8 GB / FP16 2.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Kimodo-SOMA-RP-v1.2 2026-10-13 The Kimodo model family includes models trained on different skeletons and datasets: Kimodo-SOMA-RP Trained on the 30-joint SOMA skeleton with the proprietary Bones Rigplay dataset. 283M params. License: nvidia-open-model-license. Runs on: need Q4 1.7 GB / Q8 1.8 GB / FP16 2.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
LiquidAI/LFM2.5-24B-A2B 2026-10-12 LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for fast, private agents on-device. Mixture-of-experts, 24B total, 2B active (64 experts, 4 per token). Context: 128K tokens (config). License: lfm1.0. Runs on: need Q4 16.2 GB / Q8 27.2 GB / FP16 49.7 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 2026-10-12 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding. Mixture-of-experts, 124B to Runs on: need Q4 98.5 GB / Q8 143.2 GB / FP16 261.2 GB; smallest fit Q4: 1× DGX Spark (128GB), Q8: 2× DGX Spark (256GB), FP16: Mac 512GB
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 2026-10-12 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 is the base vision-language checkpoint of the Nemotron 3.5 Super family. Mixture-of-experts, 124B total, 12B active (512 experts, 22 per token). Context: 256K tokens (config). License: openmd Runs on: need Q4 86.3 GB / Q8 143.8 GB / FP16 260.5 GB; smallest fit Q4: 96GB GPU (RTX Pro 6000 Blackwell), Q8: 2× DGX Spark (256GB), FP16: Mac 512GB
theforecastingcompany/t0-gamma 2026-10-12 Time series forecasting model from theforecastingcompany (HF pipeline tag; the card has no one-line description). Dense, 256M params. License: apache-2.0. Runs on: need Q4 1.7 GB / Q8 1.8 GB / FP16 2.0 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
openbmb/Trident-Qwen3VL-2B 2026-10-12 Trident-Qwen3VL-2B is a multimodal embedding model for mixed-modality retrieval. Dense, 2.1B params. Context: 256K tokens (config). License: mit. Runs on: need Q4 3.2 GB / Q8 4.2 GB / FP16 6.2 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
allenai/HiRO-ACEv2 2026-10-12 HiRO (High Resolution Output) is a diffusion model which generates downscaled fields at 3 km resolution from 100 km resolution inputs. License: apache-2.0.
OpenMOSS-Team/MOSS-Image-SFT 2026-10-11 MOSS-Image-SFT is a supervised fine-tuned text-to-image model in the MOSS-Image family from OpenMOSS, derived from MOSS-Image-Base. 5.1B params. License: apache-2.0. Runs on: need Q4 4.7 GB / Q8 7.0 GB / FP16 11.7 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
OpenMOSS-Team/MOSS-Image-Base 2026-10-11 MOSS-Image-Base is the base text-to-image model in the MOSS-Image family from OpenMOSS. 5.1B params. License: apache-2.0. Runs on: need Q4 4.7 GB / Q8 7.0 GB / FP16 11.7 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
datalab-to/indra-ocr 2026-10-10 Indra OCR is a 1M-parameter OCR model that runs on CPU. 1M params. License: openrail. Vendor-reported: "When you need the highest accuracy, on handwriting, math, complex tables and degraded scans, our managed platform runs Chandra, our stat Runs on: need Q4 1.5 GB / Q8 1.5 GB / FP16 1.5 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
vllm-sr/d3 2026-10-10 Zero shot classification model from vllm-sr (HF pipeline tag; the card has no one-line description). Dense, 26B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "d3 ranks first of the 149 entries on the official Runs on: need Q4 22.5 GB / Q8 31.7 GB / FP16 56.9 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
dmis-lab/UltraBERT-380M 2026-10-10 UltraBERT is a family of English bidirectional encoders with a native 32K context that reach on both classification and retrieval, two task families on which previous encoders had to choose a side. Dense, 430M params. License: apache-2.0. V Runs on: need Q4 2.1 GB / Q8 2.3 GB / FP16 2.7 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
dmis-lab/UltraBERT-150M 2026-10-10 UltraBERT is a family of English bidirectional encoders with a native 32K context that reach on both classification and retrieval, two task families on which previous encoders had to choose a side. Dense, 190M params. License: apache-2.0. V Runs on: need Q4 1.7 GB / Q8 1.8 GB / FP16 2.0 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/cosmos3-nano-libero10-sdg-export-S5_2 2026-10-10 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
nvidia/cosmos3-nano-libero10-sdg-export-S5_all 2026-10-10 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
Qwen/Qwen-Image-2.1-Turbo 2026-10-09 Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. 7.1B params. License: qwen-research. Runs on: need Q4 5.8 GB / Q8 9.2 GB / FP16 15.8 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
Cloudflare/clef-omni 2026-10-09 Clef-Omni is a 30B-A3B mixture-of-experts multimodal model that turns a state and a schema of typed questions into decisions. 35B params. License: apache-2.0. Runs on: need Q4 23.8 GB / Q8 39.0 GB / FP16 74.7 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
tencent/Youtu-Parsing-Omni 2026-10-09 Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Dense, 5.3B params. Context: 1M tokens (config). License: youtu-parsing. Runs on: need Q4 4.6 GB / Q8 7.1 GB / FP16 12.1 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 2026-10-09 NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. Mixture-of-experts, 75B total, 9B active (512 experts). Context: 256K tokens (config). License: openmdw-1.1. Runs on: need Q4 57.6 GB / Q8 86.3 GB / FP16 155.6 GB; smallest fit Q4: Mac 96GB, Q8: 96GB GPU (RTX Pro 6000 Blackwell), FP16: 2× DGX Spark (256GB)
LiquidAI/LFM2.5-24B-A2B-Base 2026-10-09 LFM2.5 is a new family of hybrid models designed for on-device deployment. Mixture-of-experts, 24B total, 2B active (64 experts, 4 per token). Context: 128K tokens (config). License: lfm1.0. Runs on: need Q4 16.1 GB / Q8 27.2 GB / FP16 49.6 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
nvidia/cosmos3-nano-libero10-sdg-export-D5 2026-10-09 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
cloud0day3/antalia-mini 2026-10-08 Antalia-2 Mini (version 1.0.1) is a small Turkish text-to-speech model with one voice. License: apache-2.0.
mistralai/Voxtral-Mini-4B-Realtime-Arabic 2026-10-08 Voxtral Mini 4B Realtime Arabic is a streaming speech-to-text model for Arabic dialects and Modern Standard Arabic. Dense, 4.4B params. Context: 128K tokens (config). Vendor-reported: "It outperforms several open-source and proprietary offl Runs on: need Q4 4.1 GB / Q8 6.6 GB / FP16 10.8 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
mistralai/LIDstral-Arabic 2026-10-08 LIDstral Arabic is a fast language and dialect classifier for text written in Arabic script. License: apache-2.0.
openbmb/MiniCPM-V-4.7-35B-A3B-DSpark 2026-10-08 Text generation model from openbmb (HF pipeline tag; the card has no one-line description). Dense, 389M params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 1.3 GB / Q8 1.5 GB / FP16 1.9 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
openbmb/MiniCPM-V-4.7-1B-DSpark 2026-10-08 Text generation model from openbmb (HF pipeline tag; the card has no one-line description). Dense, 214M params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 1.2 GB / Q8 1.3 GB / FP16 1.5 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/cosmos3-nano-libero10-sdg-export-S_best 2026-10-08 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
nvidia/cosmos3-nano-libero10-sdg-export-S_worst 2026-10-08 Robotics model from nvidia (HF pipeline tag; the card has no one-line description). 15B params. License: nvidia-open-model-license. Runs on: need Q4 11.4 GB / Q8 18.4 GB / FP16 33.8 GB; smallest fit Q4: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), Q8: 24GB GPU (3090 / 4090), FP16: 48GB GPU (RTX 6000 Ada / A6000)
openbmb/MiniCPM-V-4.7-35B-A3B 2026-10-07 MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 35B-A3B variant, with 35B-A3B being the first MoE model in the MiniCPM-V series. Mixture-of-experts, 35B total, 3B active (256 experts, 8 per token). Context: 256K to Runs on: need Q4 22.9 GB / Q8 38.6 GB / FP16 71.9 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
reflection/Beam-1.0-501B-A23B 2026-10-07 Beam is an open model built by Reflection. Mixture-of-experts, 501B total, 23B active (256 experts, 8 per token). Context: 1M tokens (config). License: apache-2.0. Runs on: need Q4 309.2 GB / Q8 535.5 GB / FP16 1005.4 GB; smallest fit Q4: Mac 512GB
lightonai/LightOnOCR-3-0.8B 2026-10-07 LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features. Dense, 853M params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 1.9 GB / Q8 2.3 GB / FP16 3.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
ibm-granite/granite-speech-5.0-2b 2026-10-07 Granite Speech 5.0 2B is a compact and efficient speech-language model, specifically designed for multilingual automatic speech recognition (ASR) and bidirectional automatic speech translation (AST) for English, French, German, Spanish, Por Runs on: need Q4 2.8 GB / Q8 3.7 GB / FP16 5.4 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Nemotron-3.5-Embed-1B-BF16 2026-10-07 The Nemotron-3.5-Embed-1B-BF16 model was distilled from the Nemotron-3.5-Embed-8B-BF16 embedding teacher using combined cosine distance (COS) and mean squared error (MSE) losses on multilingual text and image retrieval data. Dense, 1.6B par Runs on: need Q4 2.2 GB / Q8 2.7 GB / FP16 4.6 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Nemotron-3.5-Embed-8B-BF16 2026-10-07 Visual document retrieval model from nvidia (HF pipeline tag; the card has no one-line description). Dense, 8.4B params. Context: 256K tokens (config). License: openmdw-1.1. Vendor-reported: "Nemotron-3.5-Embed-8B-BF16 achieves state-of-the Runs on: need Q4 7.0 GB / Q8 10.6 GB / FP16 18.9 GB; smallest fit Q4: 8GB GPU (4060 / 3070), Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
openbmb/MiniCPM-V-4.7-1B 2026-10-06 MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. Dense, 1.6B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "In Instruct mode, the 1B variant continues to improve foundation Runs on: need Q4 2.1 GB / Q8 2.5 GB / FP16 3.9 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
lightonai/LightOnOCR-3-4B 2026-10-06 LightOnOCR-3-4B is the largest and most accurate model of the LightOnOCR-3 family, LightOn's new generation of lightweight end-to-end OCR models with layout and visual understanding. Dense, 4.5B params. Context: 256K tokens (config). Licens Runs on: need Q4 4.8 GB / Q8 6.9 GB / FP16 11.2 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
nvidia/RFD4-Proteina 2026-10-06 Use the RFD4 loader below; this is a native RFD4 bundle. 436M params. License: bsd-3-clause. Runs on: need Q4 1.8 GB / Q8 2.0 GB / FP16 2.4 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
LiquidAI/d1-3B 2026-10-05 d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. Dense, 3.1B params. Context: 32K tokens (config). License: lfm1.0. Runs on: need Q4 3.2 GB / Q8 4.4 GB / FP16 6.9 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
speridlabs/iris-3b 2026-10-05 Iris-3B Turbo, in the turbo/ folder of this repo, is a 4-step distilled version of Iris-3B. 3B params. License: apache-2.0. Runs on: need Q4 3.2 GB / Q8 4.7 GB / FP16 7.5 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
perplexity-ai/pplx-decider-v1.1-27b 2026-10-05 pplx-decider-v1.1-27b is an update of our pplx-decider-v1-27b model, that boost the Decision Index score from 56.4 to 61.56, now outperforming Jev by more than 3.5 points, while using the same backbone. Dense, 26B params. Context: 256K toke Runs on: need Q4 18.4 GB / Q8 30.3 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
LiquidAI/d1-omni-600M 2026-10-05 d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. Dense, 587M params. Context: 125K tokens (config). License: lfm1.0. Runs on: need Q4 1.5 GB / Q8 1.7 GB / FP16 2.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
inclusionAI/LemonDecider 2026-10-05 LemonDecider 4B is a typed decision engine: it reads a state and a question with a list of options, runs one forward pass, and returns a probability distribution over the options (choice / noul questions) or an ordered rating (score questio Runs on: need Q4 4.8 GB / Q8 6.9 GB / FP16 11.2 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
amazon/ALoDLM-8B 2026-10-02 ALoDLM is a family of diffusion language models developed at Amazon, available as ALoDLM-1.7B and ALoDLM-8B and initialized from the corresponding Qwen3 backbones. Dense, 8.2B params. Context: 40K tokens (config). License: cc-by-nc-4.0. Runs on: need Q4 7.2 GB / Q8 10.9 GB / FP16 18.6 GB; smallest fit Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
SoMarkAI/OXR-1.0 2026-10-02 OXR (Optical Everything Recognition) is an open-source model from the SoMark team. Dense, 1.5B params. Context: 40K tokens (config). Vendor-reported: "An open-source document parsing model with SOTA accuracy and speed, using an RSI loop dur Runs on: need Q4 2.4 GB / Q8 3.1 GB / FP16 4.6 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
nvidia/Flora-Rewarder 2026-10-02 Training labels are a combination of human-written annotations, automatic success signals recorded with the data, and VLM-generated annotations. Dense, 28B params. Context: 256K tokens (config). License: nvidia-license. Runs on: need Q4 19.8 GB / Q8 32.6 GB / FP16 58.7 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
amazon/ALoDLM-1.7B 2026-10-02 ALoDLM is a family of diffusion language models developed at Amazon, available as ALoDLM-1.7B and ALoDLM-8B and initialized from the corresponding Qwen3 backbones. Dense, 2B params. Context: 40K tokens (config). License: cc-by-nc-4.0. Runs on: need Q4 3.1 GB / Q8 4.1 GB / FP16 6.0 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
fishaudio/drama-3 2026-10-01 Fish Audio Drama 3 is Fish Audio's new-generation text-to-speech model, built for multi-character scenes and long-form content. Mixture-of-experts, 36B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: fis Runs on: need Q4 25.5 GB / Q8 40.2 GB / FP16 73.3 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
canberkkkkkk/ema-lightning 2026-10-01 Text to speech model from canberkkkkkk (HF pipeline tag; the card has no one-line description). License: apache-2.0.
perplexity-ai/pplx-decider-v1-27b 2026-10-01 pplx-decider-v1-27b is a decision model fine-tuned from Qwen3.8-27B. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 18.8 GB / Q8 30.8 GB / FP16 55.3 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 32GB GPU (5090), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
nvidia/PixelUMM 2026-10-01 PixelUMM is an NVIDIA-developed, encoder-free unified multimodal model for joint understanding and generation across text, images, and video directly in pixel space. License: nvidia-one-way-noncommercial-license.
nvidia/Flora-Captioner 2026-10-01 Image text to text model from nvidia (HF pipeline tag; the card has no one-line description). Dense, 27B params. Context: 256K tokens (config). License: nvidia-license. Runs on: need Q4 19.5 GB / Q8 32.2 GB / FP16 57.8 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
Cloudflare/clef 2026-09-30 Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 20.8 GB / Q8 31.9 GB / FP16 57.2 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
Cloudflare/clef-flash 2026-09-30 Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions. Dense, 9.4B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 8.1 GB / Q8 11.8 GB / FP16 20.3 GB; smallest fit Q4: 12GB GPU (RTX 3060), Q8: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), FP16: 24GB GPU (3090 / 4090)
Cactus-Compute/whistle 2026-09-30 Whistle is a log-mel front end and a convolutional stem feeding an audio encoder, read by a Needle-shaped decoder through gated cross attention at every layer. License: apache-2.0.
KittenML/kitten-tts-2 2026-09-30 Text to speech model from KittenML (HF pipeline tag; the card has no one-line description). License: stellon-labs-community-license.
speach1sdef178/MiniMax-H3-X2-Detail-VAE 2026-09-30 Image to video model from speach1sdef178 (HF pipeline tag; the card has no one-line description). License: other.
facebook/meta-encoder 2026-09-30 Feature extraction model from facebook (HF pipeline tag; the card has no one-line description). 30B params. License: apache-2.0. Runs on: need Q4 23.2 GB / Q8 35.1 GB / FP16 63.1 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
BAAI/AREX-2 2026-09-29 AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). Dense, 27B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 20.3 GB / Q8 31.8 GB / FP16 56.9 GB; smallest fit Q4: 24GB GPU (3090 / 4090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
microsoft/AesCode-8B 2026-09-29 Image text to text model from microsoft (HF pipeline tag; the card has no one-line description). Dense, 8.8B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 7.4 GB / Q8 10.9 GB / FP16 18.6 GB; smallest fit Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)
microsoft/AesCode-32B 2026-09-29 Image text to text model from microsoft (HF pipeline tag; the card has no one-line description). Dense, 33B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 23.6 GB / Q8 37.9 GB / FP16 68.6 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
internlm/AdvancedMathBench-AutoVerifier 2026-09-29 AutoVerifier is a learned grader, not a formal proof checker, and can make errors. Mixture-of-experts, 36B total (256 experts, 8 per token). Context: 256K tokens (config). Runs on: need Q4 23.3 GB / Q8 39.9 GB / FP16 74.7 GB; smallest fit Q4: 32GB GPU (5090), Q8: 48GB GPU (RTX 6000 Ada / A6000), FP16: 96GB GPU (RTX Pro 6000 Blackwell)
NaiveAI/Naive-N0.5-Flash 2026-09-27 Naive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for coding and AI R&D. Mixture-of-experts, 16B active (256 experts, 8 per token). Context: 1M tokens (config). License: mit. Vendor-reported: "SWA uses a Runs on: need Q8 2.9 GB; smallest fit Q8: 8GB GPU (4060 / 3070)
shhivv/taiga-s1 2026-09-27 Taiga-S1 is the fast "System 1" layer for a CAD agent. 1M params. License: mit. Runs on: need Q4 1.5 GB / Q8 1.5 GB / FP16 1.5 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
Aratako/Irodori-TTS-v4-Large 2026-09-27 Irodori-TTS-v4-Large is a Japanese Text-to-Speech model based on a Rectified Flow Diffusion Transformer (RF-DiT) architecture. 3.3B params. License: gemma. Vendor-reported: "v4-Large achieves higher mean CAM++ cosine similarity at all four Runs on: need Q4 3.5 GB / Q8 5.4 GB / FP16 8.5 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 12GB GPU (RTX 3060)
XiaomiMiMo/MiMo-V2.6-Flash-MOPD 2026-09-27 Text generation model from XiaomiMiMo (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 311B total, 15B active (256 experts, 8 per token). Context: 1M tokens (config). License: mit. Runs on: need Q4 188.7 GB / Q8 332.4 GB / FP16 623.7 GB; smallest fit Q4: 2× DGX Spark (256GB), Q8: Mac 512GB
XiaomiMiMo/MiMo-V2.6-Pro-MOPD 2026-09-27 Text generation model from XiaomiMiMo (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 1024B total, 42B active (384 experts, 8 per token). Context: 1M tokens (config). License: mit. Runs on: need Q4 619.0 GB / Q8 1092.7 GB / FP16 2052.9 GB
internlm/Intern-Decision-4B 2026-09-26 Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. Dense, 4.5B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 4.8 GB / Q8 6.6 GB / FP16 11.2 GB; smallest fit Q8: 8GB GPU (4060 / 3070), FP16: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080)
internlm/Intern-Decision-0.8B 2026-09-26 Intern-Decision-0.8B is a multimodal structured decision model fine-tuned from Qwen3.5-0.8B. Dense, 853M params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 1.9 GB / Q8 2.2 GB / FP16 3.1 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
internlm/Intern-Decision-2B 2026-09-26 Intern-Decision-2B is a multimodal structured decision model fine-tuned from Qwen3.5-2B. Dense, 2.2B params. Context: 256K tokens (config). License: apache-2.0. Runs on: need Q4 2.7 GB / Q8 3.4 GB / FP16 5.8 GB; smallest fit FP16: 8GB GPU (4060 / 3070)
Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview 2026-09-25 Veda is a learned sparse-attention method for video diffusion models. Dense. License: minimax-h3-community. Vendor-reported: "Visual and audio quality on par with full attention while skipping 90% of it."
perplexity-ai/pplx-embed-v2-context-9b-preview 2026-09-25 Feature extraction model from perplexity-ai (HF pipeline tag; the card has no one-line description). Dense, 8.4B params. Context: 256K tokens (config). License: mit. Runs on: need Q4 7.1 GB / Q8 11.0 GB / FP16 18.9 GB; smallest fit Q8: 12GB GPU (RTX 3060), FP16: 24GB GPU (3090 / 4090)