| { |
| "axquant_version": "1.0.1", |
| "calibration": null, |
| "created_at": "2026-08-02T21:27:43.205732Z", |
| "effective_bpw": 15.729999988979143, |
| "files": [ |
| { |
| "path": "README.md", |
| "sha256": "f02596adca7c37833e1f6b7a1ee9a226cf0aec306ece3451a907539e2a5e2f70", |
| "size_bytes": 7322 |
| }, |
| { |
| "path": "axquant_plan.json", |
| "sha256": "2c33cd6509fafdc77fc1e05fce8b97adca44715b8b7057b066e44b0ab7ee155b", |
| "size_bytes": 750434 |
| }, |
| { |
| "path": "axquant_quantizer_execution.json", |
| "sha256": "175b9551b93b9707a60f915328ab2664ce77b6b590c84527057191c291a6097f", |
| "size_bytes": 99417 |
| }, |
| { |
| "path": "axquant_runtime.json", |
| "sha256": "922f7c4e3c5b3fd6fe9ade95fa45e9bcca40f9ddfcc9c25b4b15268f68a2de96", |
| "size_bytes": 1643 |
| }, |
| { |
| "path": "chat_template.jinja", |
| "sha256": "c79a833039a43602150cce0902403d6e376c50930c1b2a139b2964e1f0c322a0", |
| "size_bytes": 6068 |
| }, |
| { |
| "path": "config.json", |
| "sha256": "6f5001ad96287d5b6f6379b64aa0a3d685f51bd3df1cd3aa028b27611cf270cc", |
| "size_bytes": 115754 |
| }, |
| { |
| "path": "generation_config.json", |
| "sha256": "37a3c1ef63516ca489c575f0db1c0405ddc0c3dbaca9ed987344c966c37aeef5", |
| "size_bytes": 214 |
| }, |
| { |
| "path": "model-00001-of-00036.safetensors", |
| "sha256": "dc774ff54642096057231ab55ae891dba1cc97aef70898c69dd311be9977cd65", |
| "size_bytes": 4667646207 |
| }, |
| { |
| "path": "model-00002-of-00036.safetensors", |
| "sha256": "147bb434702bdea67ad56dd024a6d3d98c698cbb5fdbc7b9c5168f49855db287", |
| "size_bytes": 4316886647 |
| }, |
| { |
| "path": "model-00003-of-00036.safetensors", |
| "sha256": "8ff5972db1d21133966f5697b199a26bbc2050519b88dde1ad1c54bcc22fefef", |
| "size_bytes": 4335250747 |
| }, |
| { |
| "path": "model-00004-of-00036.safetensors", |
| "sha256": "7a5dea09d970d9c9774a055502c2a1a5e0cd10c4c96e68de2e5c2edad504ce21", |
| "size_bytes": 4316886649 |
| }, |
| { |
| "path": "model-00005-of-00036.safetensors", |
| "sha256": "499a1b97a59cae2043c4fbf9ef1c5dafa252350b3cf2362c51e8084723f530ec", |
| "size_bytes": 4316886647 |
| }, |
| { |
| "path": "model-00006-of-00036.safetensors", |
| "sha256": "14b3b51a52349aaac2bd2d533b0004c6d78d6202339dba0785a9248587b64857", |
| "size_bytes": 4337347869 |
| }, |
| { |
| "path": "model-00007-of-00036.safetensors", |
| "sha256": "a27924bdf74705bd65b71dd69e3012f75f98c5f703728e4fad7108270b851e96", |
| "size_bytes": 4318983803 |
| }, |
| { |
| "path": "model-00008-of-00036.safetensors", |
| "sha256": "f5ead4fa04dfcf6a81ec592a4e0557329beb4f2b0b3ed7421c8e9db837a0b375", |
| "size_bytes": 4318983821 |
| }, |
| { |
| "path": "model-00009-of-00036.safetensors", |
| "sha256": "68c19065c09f0e7dea2ec8abb6a66d88d4eaa4c12ac99fe361c5885ebe82b9ab", |
| "size_bytes": 4338920812 |
| }, |
| { |
| "path": "model-00010-of-00036.safetensors", |
| "sha256": "17df4ea7f99a1ce45a3b9fb3bf01d53dd725b6c04ca3f6b01b207fb4b5735e1b", |
| "size_bytes": 4318983837 |
| }, |
| { |
| "path": "model-00011-of-00036.safetensors", |
| "sha256": "44741e6c3f72b635cf2b728c1157e2e4d7f8a31f4d4bc2dcc10a9f185ea340e0", |
| "size_bytes": 4318983803 |
| }, |
| { |
| "path": "model-00012-of-00036.safetensors", |
| "sha256": "a6701a8b290d3971f7390ca76adb3a21b37c2e6ed4baeeaf6fb784d4d7b1ba63", |
| "size_bytes": 4338920816 |
| }, |
| { |
| "path": "model-00013-of-00036.safetensors", |
| "sha256": "3eac19a2dbf194d8a156756476636ee4a18339e3cccdb2553666b1a0bbb8c604", |
| "size_bytes": 4318983777 |
| }, |
| { |
| "path": "model-00014-of-00036.safetensors", |
| "sha256": "3ec56cc36940d9bf23824cb2a09b6cffde6205ece5d75bd12b45986185cde950", |
| "size_bytes": 4318983721 |
| }, |
| { |
| "path": "model-00015-of-00036.safetensors", |
| "sha256": "60f0f90fdfc7114a006de257b30964efcbcd9af289eb4f79961bc4da06511ecb", |
| "size_bytes": 4338920784 |
| }, |
| { |
| "path": "model-00016-of-00036.safetensors", |
| "sha256": "7a55bc98101bcb53d59d755d3e60ba5b429a5366b72c188619f738518a3bf245", |
| "size_bytes": 4318983779 |
| }, |
| { |
| "path": "model-00017-of-00036.safetensors", |
| "sha256": "241fcd877a9a8f64959f2cf5b8ce1bb11e76938d4174eadebb779fadedf02977", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00018-of-00036.safetensors", |
| "sha256": "2e5dae70cd7426322234996d108c6364b7f4eae5d19fedb3602f50b89c8cb246", |
| "size_bytes": 4338920808 |
| }, |
| { |
| "path": "model-00019-of-00036.safetensors", |
| "sha256": "445a59f6e152e60d7c3cca83cbed4aa78c98288d8e4ec59cf040dd0a35b0ffc9", |
| "size_bytes": 4318983837 |
| }, |
| { |
| "path": "model-00020-of-00036.safetensors", |
| "sha256": "806ae8142c94c7f49ab076e6ff09c5afe784b7a435e8f74604928eae423c21d4", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00021-of-00036.safetensors", |
| "sha256": "d65ea01683bd38e08da8f034a25aadc58dd89f058b789ec24e66f3abf9c84814", |
| "size_bytes": 4338920786 |
| }, |
| { |
| "path": "model-00022-of-00036.safetensors", |
| "sha256": "969797d65b8c29f28071d307419b741473b6036262d021bcbce8f33a09ecf945", |
| "size_bytes": 4318983717 |
| }, |
| { |
| "path": "model-00023-of-00036.safetensors", |
| "sha256": "5904416199a33d4c951531f85464b6a85ca54bfdf04371fdf0455542c0f19f09", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00024-of-00036.safetensors", |
| "sha256": "8aaac4909c93251bf6cff09eb060473e79d2b26cd600b82be316e82b269039d4", |
| "size_bytes": 4338920788 |
| }, |
| { |
| "path": "model-00025-of-00036.safetensors", |
| "sha256": "f38499e4d4dbb6b32f5b1ebd6bc132c62eee918ad93f3e9ab887f1bc894beebb", |
| "size_bytes": 4318983837 |
| }, |
| { |
| "path": "model-00026-of-00036.safetensors", |
| "sha256": "5110868f93908066ac0578d016bbf4554fd87327eb4091ecea28c1441eda47c2", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00027-of-00036.safetensors", |
| "sha256": "4b45addb03f62d686cf382642cb402fe027ad78a9366c95ae067bf6cbbb3f0f6", |
| "size_bytes": 4338920830 |
| }, |
| { |
| "path": "model-00028-of-00036.safetensors", |
| "sha256": "ac4562e9b284b08682016a5a59e49686976aef97c1f7a2ea59b0117ce7713582", |
| "size_bytes": 4318983837 |
| }, |
| { |
| "path": "model-00029-of-00036.safetensors", |
| "sha256": "b0cc15f9e8423675910ac93b31c91ebb2fb9a6e656f3f1aaceab04aa47f713c8", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00030-of-00036.safetensors", |
| "sha256": "d96846709259aa89508ea643816d42b27ce053a0220909773acc0c1930a31100", |
| "size_bytes": 4338920856 |
| }, |
| { |
| "path": "model-00031-of-00036.safetensors", |
| "sha256": "45ae86597e91a900f8b59eab4d1a13b236aa6280b91e5b6e675e33c8b0ea617f", |
| "size_bytes": 4318983837 |
| }, |
| { |
| "path": "model-00032-of-00036.safetensors", |
| "sha256": "a6abd87dcb3b12fac1e3a2056bba034cef194e12a1dcf42b25b99317c54a04d4", |
| "size_bytes": 4318983835 |
| }, |
| { |
| "path": "model-00033-of-00036.safetensors", |
| "sha256": "ab9d7757ce12a417160189ade3f891f5744fb1a0b93be7ddc1d9fad986e90bc1", |
| "size_bytes": 4338945408 |
| }, |
| { |
| "path": "model-00034-of-00036.safetensors", |
| "sha256": "3fd6616ea143a1a20d1d5666a4fdd2492cf0de6b0d1a78c6a0a6b2c6aa09088c", |
| "size_bytes": 4319008413 |
| }, |
| { |
| "path": "model-00035-of-00036.safetensors", |
| "sha256": "6258649c5d9b856d1e37bc1b7958840f57f42aeffef15647ee936f393d34c86e", |
| "size_bytes": 4319016603 |
| }, |
| { |
| "path": "model-00036-of-00036.safetensors", |
| "sha256": "6fdef425b265a7fbcc54f67bb899989fe87ed2aa762f91124986cd758afd28c1", |
| "size_bytes": 4939012116 |
| }, |
| { |
| "path": "model.safetensors.index.json", |
| "sha256": "fde6f042726565f6d02117b0e7d18f6e6bd09222d71602375f87b1369be0184f", |
| "size_bytes": 146219 |
| }, |
| { |
| "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": 156659962402, |
| "measured_main_bpw": 15.730019129483077, |
| "measured_total_bpw": 15.730019129483077, |
| "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": "e78d2b28e28cc14bcbfe9bedf61bd436d875f375a77f000f3a68837890e3d881", |
| "profile": "general", |
| "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": "runtime-dependent", |
| "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": "2026-08-02T21:26:21.520101Z", |
| "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": "native", |
| "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": "1.0.1", |
| "mlx": "0.32.0", |
| "mlx_lm": "0.31.3", |
| "pydantic": "2.13.4", |
| "python": "3.13.14", |
| "safetensors": "0.8.0" |
| }, |
| "source_model": { |
| "architecture": "Qwen3NextForCausalLM", |
| "format": "mlx", |
| "local_path": null, |
| "model_id": "Qwen/Qwen3-Coder-Next", |
| "revision": null |
| }, |
| "target_class": "4bit", |
| "weight_distribution": { |
| "4bit": { |
| "fraction": 0.021217981894828382, |
| "parameters": 1690529792 |
| }, |
| "6bit": { |
| "fraction": 4.9866963968879015e-06, |
| "parameters": 397312 |
| }, |
| "8bit": { |
| "fraction": 0.00453717399179112, |
| "parameters": 361496576 |
| }, |
| "bf16": { |
| "fraction": 0.9742398574169836, |
| "parameters": 77621967616 |
| } |
| }, |
| "weight_file_size_bytes": 156659962402 |
| } |
|
|
