{
  "axquant_version": "1.9.0",
  "calibration": null,
  "created_at": "2026-08-18T18:30:00.469669Z",
  "effective_bpw": 5.059036550784871,
  "files": [
    {
      "path": "README.md",
      "sha256": "3ff9059cef0b40f6f1405cb3462f394a32199c0eed75623e974daee5dfed95ec",
      "size_bytes": 8683
    },
    {
      "path": "axquant_plan.json",
      "sha256": "a83a02c5cec9f5065654fcdb071bf4d48ee74370ebbff2f8ac9377834866c65b",
      "size_bytes": 67900706
    },
    {
      "path": "axquant_quantizer_execution.json",
      "sha256": "a7b7024c8a74a126aeead3162b55f4b923939b474c4b88a170138b5584281414",
      "size_bytes": 18745977
    },
    {
      "path": "axquant_runtime.json",
      "sha256": "06d0b8ad801cc8d8a7d4ed799848088fec2381c110cf98d1da5ae548b6bfb30d",
      "size_bytes": 1628
    },
    {
      "path": "chat_template.jinja",
      "sha256": "c79a833039a43602150cce0902403d6e376c50930c1b2a139b2964e1f0c322a0",
      "size_bytes": 6068
    },
    {
      "path": "config.json",
      "sha256": "fc1e86652df25bc7dc455035a33dbd02c09deb91908ec2aad33f20e929dab6cf",
      "size_bytes": 156950
    },
    {
      "path": "generation_config.json",
      "sha256": "37a3c1ef63516ca489c575f0db1c0405ddc0c3dbaca9ed987344c966c37aeef5",
      "size_bytes": 214
    },
    {
      "path": "model-00001-of-00009.safetensors",
      "sha256": "25e0609df75f20e2d00380d92950b49ee112de291234a77a96bc222d4c1e5f4e",
      "size_bytes": 5298640091
    },
    {
      "path": "model-00002-of-00009.safetensors",
      "sha256": "3d6a034a16a0a9fc1681d0654620b7aaf86781bd4b50b2730905d5f51585f1e3",
      "size_bytes": 5251437577
    },
    {
      "path": "model-00003-of-00009.safetensors",
      "sha256": "1cac58ec604e6fa9255d6541f388056b3d505dca44c5d82c7b2f75d5267f1477",
      "size_bytes": 5254914577
    },
    {
      "path": "model-00004-of-00009.safetensors",
      "sha256": "1f5d1903eed4f9b1785174a28f13cc870de4f765d2484ed4b84764b1371e9e51",
      "size_bytes": 5251437678
    },
    {
      "path": "model-00005-of-00009.safetensors",
      "sha256": "25117fa9ceebe5dcd156850b540bc76da9d30c53bbbf2b367ae244ae302a861f",
      "size_bytes": 5254914611
    },
    {
      "path": "model-00006-of-00009.safetensors",
      "sha256": "b4f5a246c38f81d5cad012bac46de7cb2e9900a16dad48209677482216dfc303",
      "size_bytes": 5251437708
    },
    {
      "path": "model-00007-of-00009.safetensors",
      "sha256": "625f136ddd98f53968cf4e34c217e3a95e36c32d9b593d236c0fad683e73aae6",
      "size_bytes": 5254914607
    },
    {
      "path": "model-00008-of-00009.safetensors",
      "sha256": "74234c80e06ab56f4d8af0918e8a3cd41223e6b1bfa210f369488b7b6e74e30b",
      "size_bytes": 5251437720
    },
    {
      "path": "model-00009-of-00009.safetensors",
      "sha256": "dfb10b70f81105971143f8d0ee3ae65fd435604e4d0b428d3df3cd0e77a45a52",
      "size_bytes": 909221492
    },
    {
      "path": "model.safetensors.index.json",
      "sha256": "7381ca01ebfa27aa1b45668f5bcc2c4bb2b6e53de49fd6763a04844c9cfd116a",
      "size_bytes": 131598
    },
    {
      "path": "qwen3_coder_detector_sgl.py",
      "sha256": "e5a6112dd41df1580ede5f52e928e58cb74985dfa5628fd94073fd6a0f20fb8d",
      "size_bytes": 19855
    },
    {
      "path": "qwen3coder_tool_parser_vllm.py",
      "sha256": "e6ad932aaa29a4004d592ca655c3d1ad849525a498ba60a716909ec9c1fda297",
      "size_bytes": 31680
    },
    {
      "path": "tokenizer.json",
      "sha256": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506",
      "size_bytes": 11422650
    },
    {
      "path": "tokenizer_config.json",
      "sha256": "23ff856b54c821dbd7e3fbcb9f33bd514f03a1ce194390d51bebae7de5a601be",
      "size_bytes": 731
    }
  ],
  "format": "mlx",
  "logical_parameters": 79674391296,
  "main_logical_parameters": 79674391296,
  "main_weight_file_size_bytes": 42978356061,
  "measured_main_bpw": 4.31539975260861,
  "measured_total_bpw": 4.31539975260861,
  "mtp_acceptance_retention": null,
  "mtp_distribution": {},
  "mtp_measured_speedup": null,
  "mtp_policy": {
    "candidate_bits": [
      8,
      16
    ],
    "min_bits": 8,
    "mode": "protected",
    "optimize_for_acceptance": true,
    "preserve_external_sidecar": true,
    "protect_norms": true,
    "protect_output_head": true
  },
  "mtp_present": false,
  "mtp_weight_file_size_bytes": 0,
  "plan_sha256": "02567ac858019017a3421bcf536f3b748a1491abd64cd8416bda2942568023f1",
  "profile": "agent-coding",
  "protected_weight_file_size_bytes": 0,
  "quantizer": "axquant",
  "runtime": {
    "ax_engine": {
      "decode_kernel": null,
      "fused_mtp": null,
      "kernel_evidence": "unmeasured",
      "model_manifest": "model-manifest.json",
      "preferred_group_size": 32
    },
    "compatible_runtimes": [
      {
        "compatibility_level": "B",
        "manifest": "config.json",
        "mtp_support": "none",
        "name": "mlx-lm",
        "notes": [
          "Standard backbone inference is the compatibility target.",
          "AXQuant MTP metadata may be ignored by MLX-LM."
        ],
        "standard_inference": true,
        "standard_mlx_weights": true,
        "support_level": "standard-inference"
      }
    ],
    "created_at": "2026-08-18T18:27:54.487021Z",
    "kv_cache": null,
    "memory_policy": {
      "kv_cache_precision": "runtime-default",
      "mtp_buffers": "not-required",
      "prefix_cache": "runtime-managed",
      "unified_memory_safety_margin": "benchmark-required"
    },
    "mtp": {
      "acceptance_retention": null,
      "detected": false,
      "draft_tokens": null,
      "enabled_by_default": false,
      "head_precision": null,
      "measured_speedup": null,
      "optimized": false,
      "recommended_temperature_max": null,
      "sidecar_file": null,
      "verification_mode": null
    },
    "optimization_scope": "text-path",
    "primary_runtime": {
      "compatibility_level": "A",
      "manifest": "model-manifest.json",
      "mtp_support": "none",
      "name": "ax-engine",
      "notes": [
        "Runtime claims require a passing AX Engine doctor and benchmark report."
      ],
      "standard_inference": true,
      "standard_mlx_weights": true,
      "support_level": "optimized"
    },
    "schema_version": "axquant.runtime.v1"
  },
  "schema_version": "axquant.artifact.v2",
  "software_versions": {
    "ax_engine": null,
    "axquant": "1.9.0",
    "mlx": "0.32.0",
    "mlx_lm": "0.31.3",
    "pydantic": "2.13.4",
    "python": "3.12.13",
    "safetensors": "0.8.0"
  },
  "source_model": {
    "architecture": "Qwen3NextForCausalLM",
    "format": "mlx",
    "local_path": null,
    "model_id": "Qwen/Qwen3-Coder-Next",
    "revision": "a7fbcb5c0e12d62a448eaa0e260346bf5dcc0feb"
  },
  "target_class": "5p6bpw",
  "weight_distribution": {
    "4bit": {
      "fraction": 0.9915386718739344,
      "parameters": 79000240128
    },
    "8bit": {
      "fraction": 0.0045384078135800405,
      "parameters": 361594880
    },
    "bf16": {
      "fraction": 0.003922920312485546,
      "parameters": 312556288
    }
  },
  "weight_file_size_bytes": 42978356061
}