Files
lai_automatisierung/benchmarks/inference/direct-results/20260831T133721Z-qwen3.8-27b-mxfp8/summary.json
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

22 lines
709 B
JSON

{
"runtime": "mlx-lm-direct",
"model": "qwen3.8-27b-mxfp8",
"requests": 5,
"successes": 5,
"ttft_s_mean": 0.6405866249930113,
"ttft_s_p50": 0.6006166669540107,
"ttft_s_p95": 0.993492508213967,
"total_s_mean": 8.97830267478712,
"total_s_p50": 8.952084249991458,
"total_s_p95": 9.543902474397328,
"prompt_tps_mean": 77.25518114106583,
"prompt_tps_p50": 69.803885982221,
"prompt_tps_p95": 108.54351756783554,
"decode_tps_mean": 15.141694584402668,
"decode_tps_p50": 15.417877788139895,
"decode_tps_p95": 15.90376325022775,
"request_tps_mean": 14.036390549836813,
"request_tps_p50": 14.298346220336581,
"request_tps_p95": 14.998850485179887,
"peak_memory_gb": 28.05746427
}