vllm-sr/d3
main boardmodel
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 text board and is on its Pareto frontier: no entry with as many parameters or fewer scores higher."
- Vendor-reported: d3 ranks first of the 149 entries on the official text board and is on its Pareto frontier: no entry with as many parameters or fewer scores higher.
- Org
- vllm-sr
- Released
- 2026-10-10
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 26.1B
- Architecture
- dense · Qwen3_5Model
- Context
- 262,144 tokens
- Task
- zero-shot-classification · other
- Signal
- 270 HF likes · 7079 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~22.5 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.7 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~56.9 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-10-10 · updated 2026-10-10 · markdown · JSON