Text Generation
MLX
Safetensors
English
Chinese
minimax_m3_vl
axquant
Mixture of Experts
minimax
experimental
not-certified
mxfp4
conversational
custom_code
4-bit precision
Instructions to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4 with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
| { | |
| "axquant_version": "1.6.2", | |
| "calibration": null, | |
| "created_at": "2026-08-23T03:42:08.686780Z", | |
| "effective_bpw": 5.061050118591269, | |
| "files": [ | |
| { | |
| "path": "added_tokens.json", | |
| "sha256": "63f277741fb061e615cb604286a845d971178ba4716732a59cf42b3752c0ce4e", | |
| "size_bytes": 1660 | |
| }, | |
| { | |
| "path": "ax_expert_stream.json", | |
| "sha256": "c69e0521c60a862bf9dabcc9b6b84ac2e8d8d2a837c8b91fa50527435816146f", | |
| "size_bytes": 98119 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "c041336a80d58cabb83f482dfeb5b3b83ba03be4933d4a4f88afd86cf8c0b388", | |
| "size_bytes": 22674747 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "ff89bfa31cc0b9b0c8a6b987ee0a52a9587650a2947ea68a504227b9dfb09bfe", | |
| "size_bytes": 6157296 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "fe2f5b2152fd4034186a7a153fb1d6267c45972533c59daa80fed5f59d973429", | |
| "size_bytes": 1716 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "b4742e8014f36c33324a15b89ee0be0929466b3fba2a83e4b464a67bf9465c7a", | |
| "size_bytes": 1201 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "11421244f67553498e5c8112dae02802025bcc4305ec45ad380af95c96f9fe64", | |
| "size_bytes": 11756 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "42850532a3bf375e5114fc3f1f687d1e0a08e77ee3c0e634800dd3c9c56b95f4", | |
| "size_bytes": 258783 | |
| }, | |
| { | |
| "path": "configuration_minimax_m3_vl.py", | |
| "sha256": "836c3e4aff06f88bd2891b18292424ed7a90158b508d9235d490a33d9e3cba32", | |
| "size_bytes": 4356 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "272d19efac5060ff8c9f76c7ed67909a5da1be466284ee4f1f1bd2a810c6fad2", | |
| "size_bytes": 150 | |
| }, | |
| { | |
| "path": "image_processor.py", | |
| "sha256": "8218f98634c365608a98ea887bfebac37131ec2acdb8445188350490de7cf994", | |
| "size_bytes": 7856 | |
| }, | |
| { | |
| "path": "merges.txt", | |
| "sha256": "ca47ea60cf5bd48832586adc264f439d0ea4254176b24a95f85eaa9750e2b5f9", | |
| "size_bytes": 2414077 | |
| }, | |
| { | |
| "path": "model-00001-of-00060.safetensors", | |
| "sha256": "ea6fe98100c966b83424ea10531d5c1b7a734ddfd0f32709b10dd0bfac4205d2", | |
| "size_bytes": 4916773008 | |
| }, | |
| { | |
| "path": "model-00002-of-00060.safetensors", | |
| "sha256": "982e2ea5b2aedf2133c50469ec0e88c125c87d3a7043619ee9c1f3c007cfffbb", | |
| "size_bytes": 4290377016 | |
| }, | |
| { | |
| "path": "model-00003-of-00060.safetensors", | |
| "sha256": "18cd228b564f3a6652a8c6a8e9d8baa86b5d46ea1bfebd6046bc64c4be80a349", | |
| "size_bytes": 4293115416 | |
| }, | |
| { | |
| "path": "model-00004-of-00060.safetensors", | |
| "sha256": "c47d5e43a9fe04f36e42cd2007529dbc85d4ce7c88e8b0a13130ed955ac40453", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00005-of-00060.safetensors", | |
| "sha256": "9dbf51a22fb3a46b2020bb673db3ba08c7e12995c9c58afebb1038cae990537e", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00006-of-00060.safetensors", | |
| "sha256": "22c737dff004347d3708717baf49d4141fefb7d6d80a4800abffafd62fc848f8", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00007-of-00060.safetensors", | |
| "sha256": "ac513a22f025010f6a9ac0c71e58f2ec189bd47cf1cd4606e0c351b4adb8acca", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00008-of-00060.safetensors", | |
| "sha256": "25d128f5937787fb221b9dedc5282a85dec9b4e8682ef53e46f846a0f328f656", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00009-of-00060.safetensors", | |
| "sha256": "2a0167a443de053e55b6293eb6dec8840b6ecb98c4844f7fdf75bb73339d4d9e", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00010-of-00060.safetensors", | |
| "sha256": "ad61fb05d4fbf1a3f99b209f3a11ba19636061688cec51cbc4fa4a38037d11eb", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00011-of-00060.safetensors", | |
| "sha256": "0fddda9bd6b607f8b802156ced3daa6cde9cb8251e01b06c514eeae7658a5fba", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00012-of-00060.safetensors", | |
| "sha256": "5bab40fca97bca0406201b7c64ffc57c3a8ea3e8b2f7a768fd5953fbc5cca934", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00013-of-00060.safetensors", | |
| "sha256": "32bbc8a31766c22f47b0d8decbb58fcad87bc4364d82047bf16336d5f0353302", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00014-of-00060.safetensors", | |
| "sha256": "953c46861982b5c6b109b8096a51fb0211461aa2965fe44265f3aa21ad2fb7d3", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00015-of-00060.safetensors", | |
| "sha256": "e0390687c4db9e366f73ac0a9b22c81cf17f6ba23f1e4d68989f1cc810c821a4", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00016-of-00060.safetensors", | |
| "sha256": "4022348ad08d5142e1e888c57cb0515064e1a02cb2ecc82cfa1815de568b75e9", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00017-of-00060.safetensors", | |
| "sha256": "70e2d370470ab132b90f8b43fe0df238ebb4f4c54e425249d5257afc4db1a33d", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00018-of-00060.safetensors", | |
| "sha256": "4ddc93626bbceca5252f3c01e228af59df7539d81db4ef8613dd4619de8b4260", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00019-of-00060.safetensors", | |
| "sha256": "a3ba729d77b1b726bd88fa35f4c778c65dcb8fd09c2bdada826507ac271d8f2f", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00020-of-00060.safetensors", | |
| "sha256": "635fcb554545e1ba3d1785a68522f91e7fa733c31e6eeb7c4a57f2ada1f549a7", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00021-of-00060.safetensors", | |
| "sha256": "4c2286becf2c6f2ace8d952dca1d12e2f66773cbc91f81923b0ecf7b52edee4f", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00022-of-00060.safetensors", | |
| "sha256": "c5415965906e5dd0a932daa30938ebb707945ecc2ed734ba2657ff9fd5c369a4", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00023-of-00060.safetensors", | |
| "sha256": "857df902be830d23440e677e4ad9d830646ac3459c94f2fedf7b7f9b748cc7e4", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00024-of-00060.safetensors", | |
| "sha256": "5223e7d558454ff350d1f06c8ce1713851fa335fac78679b1d2f5962fd3b638f", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00025-of-00060.safetensors", | |
| "sha256": "5c6ab0f392e7315e6e5f477618d4c64ac2d48ba6435250f545790d765c7b4d5b", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00026-of-00060.safetensors", | |
| "sha256": "f596ed7faca6c403070c6205d46847d289c56869c6af13d69de6bfccf04e0a79", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00027-of-00060.safetensors", | |
| "sha256": "ef90a2087a0bf460206a484282a68d9cb785a669970b8783a122f31dce7d7b7c", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00028-of-00060.safetensors", | |
| "sha256": "0b393fc2f257cdd43070a646228030272d9f18f37b81a67b5760003415d59b18", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00029-of-00060.safetensors", | |
| "sha256": "66a49676193f789a164c1359d0f09622d74c02b13c20013e5b973e06c42a00a0", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00030-of-00060.safetensors", | |
| "sha256": "0b4cd1d7761a8381ec7aeca36a7a4db3e0a865f15f569f908825f8b2de71bc64", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00031-of-00060.safetensors", | |
| "sha256": "28e0251d634958ef407a8a5cd104270804d742a5ac30287cd8ff9d1cde33a535", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00032-of-00060.safetensors", | |
| "sha256": "998bdf9cc288a79a8452c73d0c7862a590a3f1033a0b3c97dbe3eceb09a83ec2", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00033-of-00060.safetensors", | |
| "sha256": "1db4d7942bff9496f94b611c6fcd2aa5b296aa8322bf0126f8bb40ede0e6ec04", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00034-of-00060.safetensors", | |
| "sha256": "95201303f920dba0da355d5839b1de594d917e1d1caca38f6e83697849b0c34c", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00035-of-00060.safetensors", | |
| "sha256": "8c6f9f585a14a0c49b45bb8fd9a0b5a14dc1e8ee4308016f8b8d13299977c7d9", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00036-of-00060.safetensors", | |
| "sha256": "7387031381370f75f88a9fe86a5ed6f842ad00fbe381ef2aba1c214ab1b3281c", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00037-of-00060.safetensors", | |
| "sha256": "308558bb7f56784725b7c44fead2795c14e65c87bb651f5889a942d689197fc4", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00038-of-00060.safetensors", | |
| "sha256": "cb32e0a502471fad2ea6ca38b41bc0741c35ea95e37d25e0ae2c83101cc3bc8f", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00039-of-00060.safetensors", | |
| "sha256": "67add5cb07dea195bba3362a92c9476bb6f61015b3d0c16a663bdf14556c33ed", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00040-of-00060.safetensors", | |
| "sha256": "416be8c54427daed9d2c23ee1b466ec7d3d40540207d3b5a033de358a535876d", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00041-of-00060.safetensors", | |
| "sha256": "f4aac1e59cafc123512c167c4620c8a2fe77f9e3138d0b1b8fffed0be7739ca0", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00042-of-00060.safetensors", | |
| "sha256": "91d74b65d7a6df4c8805d91a09533bc054f9b7d5d07ff5586f5ddd15d2f0fe88", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00043-of-00060.safetensors", | |
| "sha256": "da563863266cb0b6dfbd87aebf90273e21706a4ff1cc57b3e94d1a8c5230a01f", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00044-of-00060.safetensors", | |
| "sha256": "68300aec4dfa775ef32f9a40548c0f96e7772df88ed996e118d7df775c9e25a1", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00045-of-00060.safetensors", | |
| "sha256": "2d661c6628735b19db029ef511b6bf2d085bc5174e8e4cd76d800475a469354b", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00046-of-00060.safetensors", | |
| "sha256": "c84bc78d141956571f42368f50fd18fab7206eb6c40f35af8f4821a33574c11a", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00047-of-00060.safetensors", | |
| "sha256": "93c3e0e1eea6507a2e8cd2b8db2273fe7b3f87f70353840f0791bad8f86e9f1c", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00048-of-00060.safetensors", | |
| "sha256": "b08c40755031e103ad097a9e940a5bbcba201c037a68250e1084e9a7ea5812ef", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00049-of-00060.safetensors", | |
| "sha256": "84d7f641db9431389a3cbc03c5a6a2a8f40bca7c21d107eaf6d493d2fa77507e", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00050-of-00060.safetensors", | |
| "sha256": "0861805d99a43f96a9bb2d45fc454e6407bcd4df8edbd94493b943b4713bc000", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00051-of-00060.safetensors", | |
| "sha256": "54c15b90de32497591a01f5dfdc19959b05ee7dfd098b268c434d70997df17fc", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00052-of-00060.safetensors", | |
| "sha256": "a79be9e58e1d8088cbb72287883acfa0bc9918fca718c26da64022a5feae30c3", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00053-of-00060.safetensors", | |
| "sha256": "d1fa4216a70b4dd239f5ba2039179aad72aae48e5775bfb58083747e851ce574", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00054-of-00060.safetensors", | |
| "sha256": "8e0305dcc4ea9cba1376098ab23d1d191608b34fc0822a24e31ca05e4eb98e3a", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00055-of-00060.safetensors", | |
| "sha256": "ce54246c9fce9ec3fb3f62d71a618ce0edcaeb17a4f7b3247b353042e27921d4", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00056-of-00060.safetensors", | |
| "sha256": "7abe72838ee9110cbb17669e36e0f199fda02ae680532b2d646d3c6846944ab0", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00057-of-00060.safetensors", | |
| "sha256": "633a3c7a1a0913ee00898c4721730d29ec9987c3216c7761a3450bb0b05a09b9", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00058-of-00060.safetensors", | |
| "sha256": "9eee9b1fd9863ba5e81b75143e8ce224c42e8cb36ba9e97690c6f79c112d0ce7", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00059-of-00060.safetensors", | |
| "sha256": "3fe1f453e1b4d63572980aacd960be0a2e5b0b1f16adeac4aa593f74efa83e8c", | |
| "size_bytes": 3850372032 | |
| }, | |
| { | |
| "path": "model-00060-of-00060.safetensors", | |
| "sha256": "6e828f5eb34b077a392ceccf7e91dbbefc5969e9e5a37163dfa29995252f811a", | |
| "size_bytes": 2566914704 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "503362d23d47fccc2137a9027e5a87cf6575862d0528e5173a51edd45f1b0973", | |
| "size_bytes": 223378 | |
| }, | |
| { | |
| "path": "preprocessor_config.json", | |
| "sha256": "36785da1dc7a00324048bd7c537c24247fca97c626884818257fd0b92287de31", | |
| "size_bytes": 772 | |
| }, | |
| { | |
| "path": "processing_minimax.py", | |
| "sha256": "0706ae8b93b3489a3b3bc7f48a5f29fb34b1449ebebb37586250e4d5fa8f5e35", | |
| "size_bytes": 9965 | |
| }, | |
| { | |
| "path": "special_tokens_map.json", | |
| "sha256": "401b624ec44507183d1dc65c74f7f3387699a77971aa19fa5a0cc57a3989ba97", | |
| "size_bytes": 277 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "bb1f1626cf01448f1e3b6036d0a061ffc66c91d9046aada14ea23a5441b5ad6e", | |
| "size_bytes": 9731500 | |
| }, | |
| { | |
| "path": "tokenizer_config.json", | |
| "sha256": "15caca9f74fbce9b86dc014e9324cbefa56703d81ccd6d56020faa1c41d2eae5", | |
| "size_bytes": 11288 | |
| }, | |
| { | |
| "path": "video_processor.py", | |
| "sha256": "ced0f8d85d73f8722fecb26033d2d91ecf4a4e5112c91ce1b1522ca7edd0943d", | |
| "size_bytes": 7318 | |
| }, | |
| { | |
| "path": "vision.safetensors", | |
| "sha256": "dc599d35c2e3d900ee7a4c77afa44f08a0755335cf853c2711c70ff295bf5b4c", | |
| "size_bytes": 1356704096 | |
| }, | |
| { | |
| "path": "vocab.json", | |
| "sha256": "b44c066b5dc34c800c4e3ecbd85f3e95ce3bfdbf8a5fe30223e005175103578a", | |
| "size_bytes": 4705413 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 427040140160, | |
| "main_logical_parameters": 427040140160, | |
| "main_weight_file_size_bytes": 233044718032, | |
| "measured_main_bpw": 4.365766982835565, | |
| "measured_total_bpw": 4.365766982835565, | |
| "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": "ac033d01d6c770838677df4c7f0fadd1119b64fd1926eab3ceb6a2848a613089", | |
| "profile": "general", | |
| "protected_weight_file_size_bytes": 1356704096, | |
| "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": "2026-08-23T03:35:14.375401Z", | |
| "kv_cache": null, | |
| "memory_policy": { | |
| "expert_stream": "required", | |
| "expert_stream_manifest": "ax_expert_stream.json", | |
| "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": "1.6.2", | |
| "mlx": "0.32.0", | |
| "mlx_lm": "0.31.3", | |
| "pydantic": "2.13.4", | |
| "python": "3.12.13", | |
| "safetensors": "0.8.0" | |
| }, | |
| "source_model": { | |
| "architecture": "MiniMaxM3SparseForConditionalGeneration", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "revision": "f0e1c1e04d40177e4673a22097036854f536e9c0" | |
| }, | |
| "target_class": "16p0bpw", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.992551479402362, | |
| "parameters": 423859322880 | |
| }, | |
| "8bit": { | |
| "fraction": 0.0029833725689642674, | |
| "parameters": 1274019840 | |
| }, | |
| "bf16": { | |
| "fraction": 0.004465148028673783, | |
| "parameters": 1906797440 | |
| } | |
| }, | |
| "weight_file_size_bytes": 233044718032 | |
| } | |