128 lines
3.5 KiB
JSON
128 lines
3.5 KiB
JSON
[
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "warmup",
|
|
"round": 1,
|
|
"prompt_name": "short",
|
|
"prompt_tokens": 20,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.46846333297435194,
|
|
"total_s": 4.887791082961485,
|
|
"prompt_tps": 84.84884256090237,
|
|
"decode_tps": 29.034596267228054,
|
|
"request_tps": 26.18769866130316,
|
|
"peak_memory_gb": 15.399948802,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "warmup",
|
|
"round": 2,
|
|
"prompt_name": "medium",
|
|
"prompt_tokens": 43,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.476554416003637,
|
|
"total_s": 4.906530833046418,
|
|
"prompt_tps": 122.50184376172285,
|
|
"decode_tps": 28.96545575207384,
|
|
"request_tps": 26.0876787195335,
|
|
"peak_memory_gb": 15.453767792,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "measured",
|
|
"round": 1,
|
|
"prompt_name": "short",
|
|
"prompt_tokens": 20,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.34607333299936727,
|
|
"total_s": 4.835503207985312,
|
|
"prompt_tps": 90.02367046337802,
|
|
"decode_tps": 28.58315107058229,
|
|
"request_tps": 26.470874797192113,
|
|
"peak_memory_gb": 15.453767792,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "measured",
|
|
"round": 2,
|
|
"prompt_name": "medium",
|
|
"prompt_tokens": 43,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.5028267079615034,
|
|
"total_s": 5.047160332964268,
|
|
"prompt_tps": 113.11164547028159,
|
|
"decode_tps": 28.2377529782062,
|
|
"request_tps": 25.360795289977208,
|
|
"peak_memory_gb": 15.453784176,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "measured",
|
|
"round": 3,
|
|
"prompt_name": "code",
|
|
"prompt_tokens": 54,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.5305347089888528,
|
|
"total_s": 5.134004874969833,
|
|
"prompt_tps": 132.97061903365554,
|
|
"decode_tps": 27.87385628056727,
|
|
"request_tps": 24.93180336155254,
|
|
"peak_memory_gb": 15.479377792,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "measured",
|
|
"round": 4,
|
|
"prompt_name": "short",
|
|
"prompt_tokens": 20,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.3781822500168346,
|
|
"total_s": 5.037674791994505,
|
|
"prompt_tps": 80.25497003795336,
|
|
"decode_tps": 27.538176565956825,
|
|
"request_tps": 25.408547650477164,
|
|
"peak_memory_gb": 15.479377792,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
},
|
|
{
|
|
"runtime": "mlx-lm-direct",
|
|
"model": "qwen3.8-27b-nvfp4-rerun",
|
|
"source": "mlx-community/Qwen3.8-27B-nvfp4",
|
|
"phase": "measured",
|
|
"round": 5,
|
|
"prompt_name": "medium",
|
|
"prompt_tokens": 43,
|
|
"output_tokens": 128,
|
|
"ttft_s": 0.5558265420258977,
|
|
"total_s": 5.245226625003852,
|
|
"prompt_tps": 102.6553925326314,
|
|
"decode_tps": 27.363511260402223,
|
|
"request_tps": 24.403140064497403,
|
|
"peak_memory_gb": 15.479377792,
|
|
"finish_reason": "length",
|
|
"error": null
|
|
}
|
|
] |