B300
22 records across 7 models (quants: BF16, FP4, FP8, MXFP4, NVFP4, as-published).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| B300 | DeepSeek-V4-Flash MoE | FP4 | vLLM | 1216 | – | – | – | – | 2026-07 | community | – | source |
| B300 | DeepSeek-V4-Flash MoE | FP4 | vLLM | 773 | – | – | – | – | 2026-07 | community | – | source |
| B300 | DeepSeek-V4-Flash MoE | FP4 | vLLM | 344 | – | – | – | – | 2026-07 | community | – | source |
| B300 | DiffusionGemma-26B-A4B | BF16 | vLLM | 1152 | – | – | 0.39 | – | 2026-10 | sourced | – | source |
| B300 | DiffusionGemma-26B-A4B | BF16 | vLLM | 947 | – | – | 0.55 | – | 2026-10 | sourced | – | source |
| B300 | GLM-5.3 | MXFP4 | vLLM | 91.6 | – | – | – | 1024 | 2026-10-22 | sourced | – | source |
| B300 | GLM-5.3 | MXFP4 | vLLM | 86.66 | – | – | – | 1024 | 2026-10-22 | sourced | – | source |
| B300 | Llama 3.3 70B 70B dense | NVFP4 | vLLM | 162.29 | – | – | – | – | 2026-06 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 10543 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 10495 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 3032 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 3012 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 464.7 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3 4B | BF16 | vLLM | 462.3 | – | – | – | tg256 | 2026-10-02 | community | – | source |
| B300 | Qwen3.6-35B-A3B | as-published | vLLM | 733 | – | – | – | – | 2026-09-25 | community | – | source |
| B300 | Qwen3.6-35B-A3B | as-published | vLLM | 460 | – | – | – | – | 2026-09-25 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 7221.04 | – | – | – | – | 2026-09-29 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 5115.53 | – | – | – | – | 2026-09-29 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 427.01 | – | – | – | – | 2026-09-29 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 286.56 | – | – | – | – | 2026-09-29 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 7.015 | – | – | – | – | 2026-09-29 | community | – | source |
| B300 | Qwen3.6-35B-A3B-FP8 35B | FP8 | vLLM | 6.419 | – | – | – | – | 2026-09-29 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085