vllm-sr/d3-flash
main boardmodel
d3-flash is the 9B multimodal foundation decision model of Decision 3.0, the decision models of vLLM Semantic Router. Dense, 8.4B params. Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "On the official text board, d3-flash is on the Pareto frontier, where no entry with as many parameters or fewer scores higher, and ranks first among the 18 entries within 0.75 to 1.33 times its size." Vendor-reported: "On the official vision board, the six Decision 3.0 models form the whole Pareto frontier: no other entry is on it. d3-flash ranks first among the three entries within 0.75 to 1.33 times its size, and fourth of 33 overall."
- Vendor-reported: On the official text board, d3-flash is on the Pareto frontier, where no entry with as many parameters or fewer scores higher, and ranks first among the 18 entries within 0.75 to 1.33 times its size.
- Vendor-reported: On the official vision board, the six Decision 3.0 models form the whole Pareto frontier: no other entry is on it. d3-flash ranks first among the three entries within 0.75 to 1.33 times its size, and fourth of 33 overall.
- Org
- vllm-sr
- Released
- 2026-10-10
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 8.4B
- Architecture
- dense · Qwen3_5Model
- Context
- 262,144 tokens
- Task
- zero-shot-classification · other
- Signal
- 101 HF likes · 102181 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~8.7 GB: 12GB GPU (RTX 3060)
- Q8 ~11.6 GB: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB, Mac 24GB
- FP16 ~20.0 GB: 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), 24GB GPU (7900 XTX), Strix Halo 128GB unified (~96GB usable), Arc B60 24GB, Arc B70 32GB, 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 2026-10-10 · updated 2026-10-10 · markdown · JSON