docs: record Qwen MLX benchmark results

benchmarks/inference/direct-results/20260831T134407Z-qwen3.8-27b-nvfp4-rerun/metadata.json

@@ -0,0 +1,48 @@
+{
+  "run_id": "20260831T134407Z",
+  "created_at": "2026-08-31T13:44:45.718463+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-rerun",
+    "warmups": 2,
+    "rounds": 5,
+    "max_tokens": 128,
+    "seed": 42,
+    "output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/direct-results"
+  },
+  "load_s": 3.153125083015766,
+  "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-rerun",
+    "requests": 5,
+    "successes": 5,
+    "ttft_s_mean": 0.46268870839849113,
+    "ttft_s_p50": 0.5028267079615034,
+    "ttft_s_p95": 0.5507681754184887,
+    "total_s_mean": 5.0599139665835535,
+    "total_s_p50": 5.047160332964268,
+    "total_s_p95": 5.222982274997048,
+    "prompt_tps_mean": 103.80325950757997,
+    "prompt_tps_p50": 102.6553925326314,
+    "prompt_tps_p95": 128.99882432098076,
+    "decode_tps_mean": 27.91928963114296,
+    "decode_tps_p50": 27.87385628056727,
+    "decode_tps_p95": 28.51407145210707,
+    "request_tps_mean": 25.315032232739288,
+    "request_tps_p50": 25.360795289977208,
+    "request_tps_p95": 26.258409367849122,
+    "peak_memory_gb": 15.479377792
+  }
+}