Files
Christian Meyer 407af8099b
Some checks failed
CI / test (push) Has been cancelled
CI / test (pull_request) Has been cancelled
docs: record Qwen MLX benchmark results
2026-08-31 16:39:37 +02:00

128 lines
3.5 KiB
JSON

[
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "warmup",
"round": 1,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 122,
"ttft_s": 1.4950010409811512,
"total_s": 8.873082707985304,
"prompt_tps": 65.2268651572191,
"decode_tps": 16.569121716474896,
"request_tps": 13.749449206667087,
"peak_memory_gb": 27.989241503,
"finish_reason": "stop",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "warmup",
"round": 2,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 0.5392710830201395,
"total_s": 8.420522083004471,
"prompt_tps": 104.9724920224018,
"decode_tps": 16.272217242824215,
"request_tps": 15.200957700514595,
"peak_memory_gb": 28.031514318,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "measured",
"round": 1,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 122,
"ttft_s": 0.41662891599116847,
"total_s": 8.074155374953989,
"prompt_tps": 69.803885982221,
"decode_tps": 15.96651063653789,
"request_tps": 15.109939595470719,
"peak_memory_gb": 28.031514318,
"finish_reason": "stop",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "measured",
"round": 2,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 0.6006166669540107,
"total_s": 8.794534499989823,
"prompt_tps": 94.30109779838891,
"decode_tps": 15.652773704987183,
"request_tps": 14.554494044016558,
"peak_memory_gb": 28.031531726,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "measured",
"round": 3,
"prompt_name": "code",
"prompt_tokens": 54,
"output_tokens": 128,
"ttft_s": 0.6342117090243846,
"total_s": 8.952084249991458,
"prompt_tps": 112.1041225101972,
"decode_tps": 15.417877788139895,
"request_tps": 14.298346220336581,
"peak_memory_gb": 28.05746427,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "measured",
"round": 4,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 122,
"ttft_s": 0.46816312498413026,
"total_s": 9.549591040995438,
"prompt_tps": 61.572468489546665,
"decode_tps": 13.468195538794124,
"request_tps": 12.775416190731752,
"peak_memory_gb": 28.05746427,
"finish_reason": "stop",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"source": "mlx-community/Qwen3.8-27B-mxfp8",
"phase": "measured",
"round": 5,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 1.0833127080113627,
"total_s": 9.521148208004888,
"prompt_tps": 48.494330924975344,
"decode_tps": 15.203115253554254,
"request_tps": 13.443756698628452,
"peak_memory_gb": 28.05746427,
"finish_reason": "length",
"error": null
}
]