kkt94/Llama-V-JEPA-LM-Qwen3-4B
archived · low-signalmodel
Llama-V-JEPA-LM-Qwen3-4B is a video-language model from the Llama-V-JEPA-LM family. Dense, 5.1B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "Trained on 4.53M public samples, Llama-V-JEPA-LM-Qwen3-4B reaches a 72.14 average on 12 scores across 11 video benchmarks, ahead of every open model of its size class (best open 4B-class model: Molmo2-4B, 61.08)." Vendor-reported: "Generalizes beyond its constructions. 96.3 average on six held-out sets (unseen speed ratios, an unseen source corpus, unseen combinations, an unseen simulator; chance 33.3), vs. 50.0 for the best open 4B-class model (Qwen3-VL-4B)."
- Vendor-reported: Trained on 4.53M public samples, Llama-V-JEPA-LM-Qwen3-4B reaches a 72.14 average on 12 scores across 11 video benchmarks, ahead of every open model of its size class (best open 4B-class model: Molmo2-4B, 61.08).
- Vendor-reported: Generalizes beyond its constructions. 96.3 average on six held-out sets (unseen speed ratios, an unseen source corpus, unseen combinations, an unseen simulator; chance 33.3), vs. 50.0 for the best open 4B-class model (Qwen3-VL-4B).
- Org
- kkt94
- Released
- 2026-11-11
- Status
- archived · low-signal
- License
- apache-2.0 (permissive)
- Parameters
- 5.1B
- Architecture
- dense · JepaLlmModel
- Context
- 262,144 tokens (config.json)
- Task
- video-text-to-text · vision
- Signal
- 9 HF likes · 108 downloads
- Archived
- 2026-11-14 (no longer listed by the collector; stats as last seen)
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~5.2 GB (estimated size): 8GB GPU (4060 / 3070)
- Q8 ~7.6 GB (estimated size): 12GB GPU (RTX 3060), Mac 16GB
- FP16 ~12.3 GB: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 24GB GPU (3090 / 4090), 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), 16GB GPU (7800 XT / 9070 XT), 24GB GPU (7900 XTX), Strix Halo 128GB unified (~96GB usable), Arc B60 24GB, Arc B70 32GB, Mac 24GB, Mac 36GB, Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 32GB RAM (slow), CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-11-11 · updated 2026-11-14 · markdown · JSON