results.json

{
 "machine": "Apple M5 Max, 137 GB, macOS 26.4.1",
 "stack": {
  "mlx": "0.32.0",
  "mlx_lm": "0.31.3"
 },
 "protocol": "interleaved A/B, 90s cooldown before each measurement, greedy, 300 tokens, K=4, GPU verified idle",
 "draft_comparison": {
  "target": "tozp/Qwen3.8-27B-OBLITERATED-V2-mlx-4bit",
  "bf16_draft": {
   "repo": "z-lab/Qwen3.8-27B-DFlash2",
   "size_gb": 3.85,
   "tok_per_s": [
    59.8,
    60.3
   ],
   "accept_pct": [
    87.9,
    87.9
   ]
  },
  "q4_draft": {
   "repo": "ProCreations/Qwen3.8-27B-DFlash2-MLXFast-Q4",
   "size_gb": 1.27,
   "tok_per_s": [
    76.1,
    76.0
   ],
   "accept_pct": [
    86.9,
    86.9
   ]
  },
  "delta": {
   "tok_per_s_pct": 26.4,
   "accept_pp": -1.0,
   "memory_gb": -2.58
  }
 },
 "target_comparison_bf16_draft": {
  "mxfp4": {
   "dense": [
    35.4,
    35.0,
    35.6
   ],
   "dflash": [
    54.0,
    54.1,
    53.8
   ],
   "accept_pct": 82,
   "token_exact": true
  },
  "heretic_ara": {
   "dense": [
    33.0,
    33.3,
    33.5
   ],
   "dflash": [
    61.7,
    62.2,
    62.3
   ],
   "accept_pct": 89,
   "token_exact": false
  },
  "obliterated_v2": {
   "dense": [
    33.0,
    33.3,
    33.6
   ],
   "dflash": [
    61.2,
    61.4,
    61.6
   ],
   "accept_pct": 88,
   "token_exact": true
  }
 },
 "server_verification": {
  "load_s": 0.9,
  "accept_rate": 0.917,
  "tok_per_s": 75.4
 },
 "thermal_drift_uncontrolled": {
  "same_measurement_start": 34.9,
  "after_3min": 26.8,
  "pct": -23
 }
}