MI355X
153 records across 9 models (quants: BF16, FP4, FP8, INT4 (a8w4), MXFP4, unspecified, unstated).
| 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 |
| 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 |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 778.70 | – | – | – | 8192 | 2026-10-01 | community | – | source |
| MI355X | DeepSeek V4.1 | FP8 | vLLM | 772.13 | – | – | – | 8192 | 2026-10-01 | 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 |
| 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 |
| 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 |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 299 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 247 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 241 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 218 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 201 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4-Pro | FP8 | vLLM | 192 | – | – | – | – | 2026-10-13 | sourced | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 343.7 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 327.4 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 318.1 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 307.2 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 299.3 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 288.0 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 265.8 | – | – | – | – | 2026-10-07 | community | – | source |
| MI355X | DeepSeek-V4.1-Flash | INT4 (a8w4) | vLLM | 214.6 | – | – | – | – | 2026-10-07 | community | contradiction | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 5399.4 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 5315.0 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4964.6 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4925.5 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4907.5 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4890.4 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4297.1 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4250.0 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4060.3 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 4042.8 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 3419.9 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 3372.9 | – | – | – | 60000 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 3118.3 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 3106.5 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 2424.7 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 2414.3 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 2248.1 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 2232.8 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1637.7 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1624.8 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1593.2 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1586.5 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1060.7 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1058.7 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1053.9 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 1051.9 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 679.3 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 674.7 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 646.2 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 645.1 | – | – | – | 8192 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 436.9 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 434.1 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 270.4 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 267.4 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 156.6 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM 5.2 | MXFP4 | vllm | 155.5 | – | – | – | 1024 | 2026-09-29 | community | – | source |
| MI355X | GLM-5.1-FP8 | FP8 | vLLM | 17042 | – | – | – | – | 2026-10-16 | sourced | – | source |
| MI355X | GLM-5.1-FP8 | FP8 | vLLM | 16616 | – | – | – | – | 2026-10-16 | sourced | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 1083.0 | – | – | – | tg1024 | 2026-09-27 | community | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 1082.6 | – | – | – | tg1024 | 2026-09-27 | community | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 668.97 | – | – | – | tg1024 | 2026-09-28 | community | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 658.42 | – | – | – | tg1024 | 2026-09-28 | community | – | source |
| MI355X | Kimi-K3 | MXFP4 | vLLM | 648 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Kimi-K3 | MXFP4 | vLLM | 647 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Kimi-K3 | MXFP4 | vLLM | 646 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Kimi-K3 | MXFP4 | vLLM | 623 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 529.7 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 515.1 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 510.9 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 499.3 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 485.5 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | FP4 | vLLM | 453.4 | – | – | – | 16384 | 2026-10-03 | community | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 236.05 | – | – | – | tg1024 | 2026-09-27 | community | – | source |
| MI355X | Kimi-K3 | BF16 | vLLM | 236.05 | – | – | – | tg1024 | 2026-09-27 | community | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 233.11 | – | – | – | 1024 | 2026-10-13 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 232.87 | – | – | – | 1024 | 2026-10-13 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 190.9 | – | – | – | – | 2026-10-14 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 180.98 | – | – | – | – | 2026-10-14 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 179.77 | – | – | – | 1024 | 2026-10-13 | sourced | contradiction | source |
| MI355X | Kimi-K3 | unspecified | vLLM | 177.3 | – | – | – | 100000 | 2026-10-07 | community | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 175.7 | – | – | – | – | 2026-10-14 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 174.25 | – | – | – | – | 2026-10-14 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 172.89 | – | – | – | – | 2026-10-06 | sourced | – | source |
| MI355X | Kimi-K3 | unstated | vLLM | 164.79 | – | – | – | 1024 | 2026-10-13 | sourced | contradiction | source |
| MI355X | Kimi-K3 | unstated | vLLM | 163.94 | – | – | – | – | 2026-10-06 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 2688.94 | – | – | – | 1024 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 2681.27 | – | – | – | 1024 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 953.94 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 942.92 | – | – | – | 1024 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 918.01 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 736.38 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 570.92 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 570.16 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 568.81 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 499.36 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 443.52 | – | – | – | 8192 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen2.5-3B-Instruct | BF16 | vLLM | 347.68 | – | – | – | 1024 | 2026-10-12 | sourced | – | source |
| MI355X | Qwen3.8-27B | BF16 | vLLM | 2762.8 | – | – | – | 1024 | 2026-10-06 | sourced | – | source |
| MI355X | Qwen3.8-27B | BF16 | vLLM | 2752.5 | – | – | – | 1024 | 2026-10-06 | sourced | – | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 1080.7 | – | – | – | 8192 | 2026-10-14 | sourced | – | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 987.1 | – | – | – | 8192 | 2026-10-14 | sourced | – | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 911.4 | – | – | – | 8192 | 2026-10-14 | sourced | contradiction | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 751.7 | – | – | – | 8192 | 2026-10-14 | sourced | contradiction | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 655.8 | – | – | – | 8192 | 2026-10-14 | sourced | – | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 579.6 | – | – | – | 8192 | 2026-10-14 | sourced | – | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 576.4 | – | – | – | 8192 | 2026-10-14 | sourced | contradiction | source |
| MI355X | Qwen3.8-27B | MXFP4 | vLLM | 430.1 | – | – | – | 8192 | 2026-10-14 | sourced | contradiction | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 1471.0 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 1457.2 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 975.3 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 964.1 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 854.7 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 684.5 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 654.0 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 642.5 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 632.2 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 491.2 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 475.5 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 462.0 | – | – | – | 8192 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 443.5 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 417.0 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 397.2 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 379.1 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 284.4 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 267.4 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 253.8 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 154.7 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 147.4 | – | – | – | 60000 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 146.8 | – | – | – | 8192 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 144.8 | – | – | – | 60000 | 2026-10-02 | community | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 143.3 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 133.0 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 123.7 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 99.8 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
| MI355X | Qwen3.8-Flash-Next | MXFP4 | vLLM | 84.5 | – | – | – | 61440 | 2026-10-13 | sourced | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085