christian.meyer/lai_automatisierung
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: record Qwen MLX benchmark results
Some checks failed
CI / test (push) Has been cancelled
Details
CI / test (pull_request) Has been cancelled
Details

Browse Source
This commit is contained in:
Christian Meyer
2026-08-31 16:39:37 +02:00
parent 75b2c8958c
commit 407af8099b
40 changed files with 6091 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

128
benchmarks/inference/direct-results/20260831T133636Z-qwen3.8-27b-nvfp4/raw.json Normal file
View File

@@ -0,0 +1,128 @@
[
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "warmup",
"round": 1,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 128,
"ttft_s": 0.6381363340187818,
"total_s": 5.067599917005282,
"prompt_tps": 46.64172306513033,
"decode_tps": 28.964400213729846,
"request_tps": 25.258505425906254,
"peak_memory_gb": 15.399916034,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "warmup",
"round": 2,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 0.46635333297308534,
"total_s": 4.885915416001808,
"prompt_tps": 122.76309757245242,
"decode_tps": 29.032294926274737,
"request_tps": 26.19775192603388,
"peak_memory_gb": 15.453767792,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "measured",
"round": 1,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 128,
"ttft_s": 0.3432638749945909,
"total_s": 4.786967416992411,
"prompt_tps": 90.81617646556052,
"decode_tps": 28.873430911706816,
"request_tps": 26.73926702438696,
"peak_memory_gb": 15.453767792,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "measured",
"round": 2,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 0.48620820802170783,
"total_s": 4.966667582979426,
"prompt_tps": 118.1052752991172,
"decode_tps": 28.63870075162873,
"request_tps": 25.771807325831702,
"peak_memory_gb": 15.453784176,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "measured",
"round": 3,
"prompt_name": "code",
"prompt_tokens": 54,
"output_tokens": 128,
"ttft_s": 0.5125948329805396,
"total_s": 5.009093041997403,
"prompt_tps": 139.56196090321154,
"decode_tps": 28.53361993265224,
"request_tps": 25.553528139089888,
"peak_memory_gb": 15.479377792,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "measured",
"round": 4,
"prompt_name": "short",
"prompt_tokens": 20,
"output_tokens": 128,
"ttft_s": 0.36031387496041134,
"total_s": 4.874560041993391,
"prompt_tps": 83.69493625406292,
"decode_tps": 28.424103574919425,
"request_tps": 26.258780053441704,
"peak_memory_gb": 15.479377792,
"finish_reason": "length",
"error": null
},
{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-nvfp4",
"source": "mlx-community/Qwen3.8-27B-nvfp4",
"phase": "measured",
"round": 5,
"prompt_name": "medium",
"prompt_tokens": 43,
"output_tokens": 128,
"ttft_s": 0.5203984580002725,
"total_s": 5.040689249988645,
"prompt_tps": 107.53363787342614,
"decode_tps": 28.384896872985717,
"request_tps": 25.393352704749322,
"peak_memory_gb": 15.479377792,
"finish_reason": "length",
"error": null
}
]