DeepSeek V4.1
48 records across 3 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 3827.03 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 3814.25 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 3182.50 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 3176.89 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 2545.75 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 2523.76 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 1793.30 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 1783.04 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 1678 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 1605 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 1595 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 1554 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 1471 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 1465 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 1273.77 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 1262.90 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 796 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 778.70 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 773 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 772.13 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 766 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 472.20 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 470.57 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 391.60 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 391.59 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | 369.892 | – | – | – | – | 2026-10-14 | sourced | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 337.69 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 335.86 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 314 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 282 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 280 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 273 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | unspecified | vLLM | 252 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 250 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 248.75 | – | – | – | 128000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 248.60 | – | – | – | 128000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 229.03 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 227.76 | – | – | – | 60000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 186.21 | – | – | – | 128000 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 185.73 | – | – | – | 128000 | 2026-10-01 | community | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | 169.756 | – | – | – | – | 2026-10-14 | sourced | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 114 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 114 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| GB300 | DeepSeek V4.1 | NVFP4 | vLLM | 114 | – | – | – | 32768 | 2026-09-30 | community | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | 82.069 | – | – | – | – | 2026-10-14 | sourced | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | 32.494 | – | – | – | – | 2026-10-14 | sourced | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | – | 15255.437 | – | – | 65536 | 2026-10-14 | sourced | – | source |
| H20 | DeepSeek V4.1 | FP8 | vLLM | – | 15265.495 | – | – | 65536 | 2026-10-14 | sourced | – | source |