docs: record Qwen MLX benchmark results

2026-08-31 16:39:37 +02:00
parent 75b2c8958c
commit 407af8099b
40 changed files with 6091 additions and 0 deletions
--- a/benchmarks/inference/direct-results/20260831T133636Z-qwen3.8-27b-nvfp4/summary.json
+++ b/benchmarks/inference/direct-results/20260831T133636Z-qwen3.8-27b-nvfp4/summary.json
@@ -0,0 +1,22 @@
+{
+  "runtime": "mlx-lm-direct",
+  "model": "qwen3.8-27b-nvfp4",
+  "requests": 5,
+  "successes": 5,
+  "ttft_s_mean": 0.4445558497915044,
+  "ttft_s_p50": 0.48620820802170783,
+  "ttft_s_p95": 0.518837732996326,
+  "total_s_mean": 4.9355954667902555,
+  "total_s_p50": 4.966667582979426,
+  "total_s_p95": 5.034370008390397,
+  "prompt_tps_mean": 107.94239735907567,
+  "prompt_tps_p50": 107.53363787342614,
+  "prompt_tps_p95": 135.27062378239268,
+  "decode_tps_mean": 28.570950408778582,
+  "decode_tps_p50": 28.53361993265224,
+  "decode_tps_p95": 28.826484879691197,
+  "request_tps_mean": 25.943347049499913,
+  "request_tps_p50": 25.771807325831702,
+  "request_tps_p95": 26.64316963019791,
+  "peak_memory_gb": 15.479377792
+}