H200
20 records across 6 models (quants: BF16, FP8, MXFP4, Q4_0, as-published, unspecified).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| H200 | DeepSeek-V4.1-Flash | unspecified | vllm | 4031.5 | – | – | – | 10000 | 2026-09-30 | community | – | source |
| H200 | DeepSeek-V4.1-Flash | unspecified | vllm | 3972 | – | – | – | 10000 | 2026-09-30 | community | – | source |
| H200 | DeepSeek-V4.1-Flash | MXFP4 | vllm | 2648 | – | – | – | 512 | 2026-09-30 | community | – | source |
| H200 | DeepSeek-V4.1-Flash | MXFP4 | vllm | 2222 | – | – | – | 512 | 2026-09-30 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 1364.4 | – | – | – | – | 2026-07 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 945.3 | – | – | – | – | 2026-07 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 525.4 | – | – | – | – | 2026-07 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 280.4 | – | – | – | – | 2026-07 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 73.9 | – | – | – | – | 2026-07 | community | – | source |
| H200 | Gemma-4-31B 31B dense | as-published | vLLM | 44.3 | – | – | – | – | 2026-07 | community | – | source |
| H200 | gpt-oss 120B 120B MoE | as-published | vLLM | 275.84 | – | – | – | – | 2026-03 | community | – | source |
| H200 | gpt-oss 120B 120B MoE | as-published | vLLM | 275.84 | – | – | – | – | 2026-03 | community | – | source |
| H200 | gpt-oss 120B 120B MoE | as-published | vLLM | 231.22 | – | – | – | – | 2026-03 | community | – | source |
| H200 | llama 7B | Q4_0 | llama.cpp (CUDA) | 337.6 | 11633.96 | – | – | tg128 | 2025-11-15 | community | – | source |
| H200 | llama 7B | Q4_0 | llama.cpp (CUDA) | 307.79 | 10428.65 | – | – | tg128 | 2025-11-15 | community | – | source |
| H200 | Qwen3-Coder-480B-A35B-Instruct-FP8 | FP8 | vLLM | 583 | – | – | – | – | 2026-10-01 | community | – | source |
| H200 | Qwen3.5-9B | BF16 | vLLM | 2069.343 | – | – | – | – | 2026-10-01 | community | – | source |
| H200 | Qwen3.5-9B | BF16 | vLLM | 1859.655 | – | – | – | – | 2026-10-01 | community | – | source |
| H200 | Qwen3.5-9B | BF16 | vLLM | 1536.536 | – | – | – | – | 2026-10-01 | community | – | source |
| H200 | Qwen3.5-9B | BF16 | vLLM | 1426.638 | – | – | – | – | 2026-10-01 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085