docs: record Qwen MLX benchmark results

benchmarks/inference/direct-results/20260831T133636Z-qwen3.8-27b-nvfp4/metadata.json

@@ -0,0 +1,48 @@
+{
+  "run_id": "20260831T133636Z",
+  "created_at": "2026-08-31T13:37:14.110488+00:00",
+  "host": {
+    "platform": "macOS-15.6-arm64-arm-64bit",
+    "machine": "arm64",
+    "python": "3.12.8"
+  },
+  "arguments": {
+    "model": "mlx-community/Qwen3.8-27B-nvfp4",
+    "label": "qwen3.8-27b-nvfp4",
+    "warmups": 2,
+    "rounds": 5,
+    "max_tokens": 128,
+    "seed": 42,
+    "output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/direct-results"
+  },
+  "load_s": 3.066661207994912,
+  "mlx_version": "0.32.0",
+  "device": "Device(gpu, 0)",
+  "prompts": {
+    "short": "In exactly four concise bullet points, explain why database transactions are useful. Do not use a heading.",
+    "medium": "You are reviewing a Laravel service that transfers money between two accounts. Explain the failure modes involving concurrency, partial writes, retries, and audit logs. Then provide a robust implementation plan. Keep the response technical and concise.",
+    "code": "Write a Python 3.12 function named merge_intervals that accepts a list of integer pairs, validates each pair, merges overlapping or adjacent intervals, and returns sorted tuples. Include type hints, a short docstring, and five assert-based examples. Output only code."
+  },
+  "summary": {
+    "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
+  }
+}