| { |
| "axquant_version": "1.2.0", |
| "calibration": null, |
| "created_at": "2026-08-05T07:23:44.193379Z", |
| "effective_bpw": 7.999220539932934, |
| "files": [ |
| { |
| "path": "README.md", |
| "sha256": "7065c607c4251d4c917a1d75f6d99d7bfe690845ad101a7e3625e540cbb30841", |
| "size_bytes": 7792 |
| }, |
| { |
| "path": "axquant_plan.json", |
| "sha256": "980597edd6f4f791380c00801791cbe653879d2bdbee5f92c25628497f548218", |
| "size_bytes": 292907 |
| }, |
| { |
| "path": "axquant_quantizer_execution.json", |
| "sha256": "f3f55fec94708899fae63efeb2b9dcdd8e3b9ee00c1ca3c08e23d4c2277bf1b9", |
| "size_bytes": 48081 |
| }, |
| { |
| "path": "axquant_runtime.json", |
| "sha256": "1f554537b6ee3c3d28ea699ba55ac722eb816e33893a4cfab06c1cee8a41614a", |
| "size_bytes": 1628 |
| }, |
| { |
| "path": "chat_template.jinja", |
| "sha256": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5", |
| "size_bytes": 4116 |
| }, |
| { |
| "path": "config.json", |
| "sha256": "2a4678d5a8f07176956241d2fddf37b099c67b4065f5e1e92d473ffb32058005", |
| "size_bytes": 54971 |
| }, |
| { |
| "path": "generation_config.json", |
| "sha256": "28396d421a2108acce96383f6a7de78008f7f1b17f807958f3c14c51dbfb65fb", |
| "size_bytes": 117 |
| }, |
| { |
| "path": "model.safetensors", |
| "sha256": "7651c905daf3832b959e312fdb0c79b408ffcdc9faafe4c7b6c672ca020f8166", |
| "size_bytes": 595796978 |
| }, |
| { |
| "path": "model.safetensors.index.json", |
| "sha256": "a3038df4a085bf07fcdedd0a5c328e6523d01c0eb36d8f99d41ffdc5d8a9959f", |
| "size_bytes": 49770 |
| }, |
| { |
| "path": "tokenizer.json", |
| "sha256": "93623af029cdc69b87f2864d3b2cc2424fdf16684f15e139b5b9d08ec34ced91", |
| "size_bytes": 11423701 |
| }, |
| { |
| "path": "tokenizer_config.json", |
| "sha256": "d93ac1a2c7adb9ad022f354d822f1f0f57e32e62ef2989e902782d6ab896acfe", |
| "size_bytes": 413 |
| } |
| ], |
| "format": "mlx", |
| "logical_parameters": 595776512, |
| "main_logical_parameters": 595776512, |
| "main_weight_file_size_bytes": 595796978, |
| "measured_main_bpw": 8.000274814459285, |
| "measured_total_bpw": 8.000274814459285, |
| "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": "3a2ba166158417fdaf008e097ac304e683383153205485c1db0bba1e2bcbaeea", |
| "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": "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": "2026-08-05T07:23:43.990411Z", |
| "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": "1.2.0", |
| "mlx": "0.32.0", |
| "mlx_lm": "0.31.3", |
| "pydantic": "2.13.4", |
| "python": "3.13.14", |
| "safetensors": "0.8.0" |
| }, |
| "source_model": { |
| "architecture": "Qwen3ForCausalLM", |
| "format": "mlx", |
| "local_path": null, |
| "model_id": "Qwen/Qwen3-Embedding-0.6B", |
| "revision": "97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3" |
| }, |
| "target_class": "8bit", |
| "weight_distribution": { |
| "6bit": { |
| "fraction": 0.3379230096268045, |
| "parameters": 201326592 |
| }, |
| "8bit": { |
| "fraction": 0.6619669893934993, |
| "parameters": 394384384 |
| }, |
| "bf16": { |
| "fraction": 0.00011000097969622542, |
| "parameters": 65536 |
| } |
| }, |
| "weight_file_size_bytes": 595796978 |
| } |
|
|
