{
  "schema_version": 1,
  "artifact": "deanzchen/Qwen3.6-27B-Q5-MTPLX",
  "hardware": {
    "chip": "Apple M5 Max",
    "gpu_cores": 40,
    "unified_memory_gib": 48,
    "power_mode_for_latest_check": "high_power"
  },
  "runtime": {
    "mtplx": "2.0.2",
    "mlx": "0.31.2",
    "mlx_lm": "0.31.3",
    "profile": "sustained",
    "generation_mode": "mtp",
    "depth": 2,
    "context_window": 262144,
    "prefill_chunk_tokens": 512,
    "trunk_quantization": "5-bit affine group64",
    "draft_head_quantization": "4-bit affine group64",
    "target_sampler": {
      "temperature": 0.6,
      "top_p": 0.95,
      "top_k": 20
    },
    "draft_sampler_for_ui_measurements": {
      "temperature": 0.6,
      "top_p": 0.95,
      "top_k": 20
    },
    "paged_kv_quantization": "off",
    "turboquant_note": "K8/V4 affects extreme-context cache capacity, not these short decode measurements."
  },
  "verification_schedule": {
    "defer_verify_hidden_eval": true,
    "verify_hidden_mode": "logits_first_committed_slice",
    "exact_token_identity_verified": true
  },
  "expected_decode_tok_s": {
    "direct_tuner_d2": {
      "expected_range": [45.0, 50.0],
      "warning_below": 45.0,
      "failure_below": 42.0,
      "workload": "mtplx long_code, thinking off, seed 0, 128 or 256 generated tokens"
    },
    "direct_tuner_d2_high_power": {
      "expected_range": [45.0, 50.0],
      "warning_below": 45.0,
      "workload": "mtplx long_code, thinking off, seed 0, 128 generated tokens"
    },
    "openai_api_code_first": {
      "expected_range": [40.0, 44.0],
      "requirement": "Send X-MTPLX-Allow-Client-Controls: 1 with enable_thinking=false."
    },
    "eight_token_smoke": {
      "expected_range": [35.0, 46.0],
      "regression_gate": false,
      "note": "Too short for stable throughput measurement."
    }
  },
  "measurements": {
    "historical_setup_128_d2": 48.799728436870346,
    "historical_comparison_256_d2": 49.90875607132132,
    "hub_direct_128_d2": 43.92720981573101,
    "hub_high_power_direct_128_d2": 45.419032271264705,
    "hub_post_reboot_high_power_direct_128_d2": 46.27235162628437,
    "hub_post_reboot_high_power_direct_128_d2_variance_5x": {
      "runs": [
        46.47503852458389,
        46.38583666459772,
        46.33124692797028,
        46.27492432091384,
        46.316507149484536
      ],
      "mean": 46.356710717510055,
      "median": 46.33124692797028,
      "sample_standard_deviation": 0.07714197438579953,
      "coefficient_of_variation_percent": 0.16640950833610618,
      "minimum": 46.27492432091384,
      "maximum": 46.47503852458389,
      "range": 0.20011420367004717,
      "all_runs_above_45": true,
      "acceptance_rate_all_runs": 1.0
    },
    "original_local_deferred_hidden_direct_128_d2_variance_5x": {
      "runs": [
        50.67376896277482,
        50.9484927857385,
        50.75530318826678,
        50.7859195241367,
        50.750990759454915
      ],
      "mean": 50.782895044074344,
      "median": 50.75530318826678,
      "sample_standard_deviation": 0.10138966296877788,
      "coefficient_of_variation_percent": 0.19965317629249388,
      "minimum": 50.67376896277482,
      "maximum": 50.9484927857385,
      "all_runs_at_or_above_48_8": true,
      "acceptance_rate_all_runs": 1.0,
      "token_sha256": "f875ce74f006ba502dac263111e6c9b1b1b4bca03648c43f670c8cae8e0a58af"
    },
    "persisted_tune_wrapper_final_gate": {
      "decode_tok_s": 49.81852161488856,
      "acceptance_rate": 1.0,
      "accepted_by_depth": [43, 42],
      "drafted_by_depth": [43, 42],
      "token_sha256": "f875ce74f006ba502dac263111e6c9b1b1b4bca03648c43f670c8cae8e0a58af",
      "text_sha256": "abc2ec0ce79cbf90e38043eeacd0fc9d34d624780e6cc630b3d5fbd0e3ced05e",
      "target_48_8_met": true
    },
    "hub_direct_256_d2_runs": [43.830748328265656, 43.695076417584225],
    "hub_api_code_first_three_run_mean": 41.46785703207608,
    "hub_api_auto_reasoning_three_run_mean": 39.68670477257572,
    "latest_ar_128": 24.149735339889887,
    "latest_d2_speedup_vs_ar": 1.916060402941681,
    "high_power_improvement_percent": 5.338699681566217,
    "post_reboot_improvement_percent": 1.878770445665201
  },
  "validation": {
    "status": "pass",
    "model_files_match_original_sha256": true,
    "direct_128_accepted_by_depth": [43, 42],
    "direct_128_drafted_by_depth": [43, 42],
    "direct_256_acceptance_rate": 0.9883720930232558,
    "conclusion": "No artifact or MTP acceptance regression. Current throughput is within the expected machine-state range."
  }
}