Text Generation
MLX
Safetensors
qwen3_5_moe
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3.5-moe
6bit
6-bit
mtp
vision
conversational
Instructions to use AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP") 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP"
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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP" # 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP"
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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP 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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP"
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-Ornith-1.5-397B-MLX-AXQ-6bit-MTP" \ --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"
Publish AX-Ornith-1.5-397B-MLX-AXQ-6bit-MTP from ornith-ai/Ornith-1.5-397B@8f6cc8a7aea505364523f84ccf37706e8aea0ee7
82817a2 verified | { | |
| "axquant_version": "1.9.0", | |
| "calibration": null, | |
| "created_at": "2026-09-07T04:00:00.493684Z", | |
| "effective_bpw": 6.6957494309767815, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "d62a94c0a299bad3fadbee01bd6a57885443a33fc59abf54c036110f1c9bae26", | |
| "size_bytes": 8399 | |
| }, | |
| { | |
| "path": "ax_expert_stream.json", | |
| "sha256": "e9f9349d376609f40c7465e3dedccf54629a4592e040953dd032268f0e17dff0", | |
| "size_bytes": 147566 | |
| }, | |
| { | |
| "path": "axquant_mtp_sidecar_manifest.json", | |
| "sha256": "4c0e86e74985e5493fbbd61859414c7bdb73db4ce3260657ab8efc4751144d60", | |
| "size_bytes": 887 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "d743e81f897f436cc318337f1ef622ef6dc42be332e8e56b9c81668977618395", | |
| "size_bytes": 2647666 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "aa05670b005b2ed7116dcd8d399cf92ad3bd9271719fbff27750c74490735208", | |
| "size_bytes": 187326 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "e9b6b0f5826d65b95c19237060d58c3174e0760091e4c1425f0c0caf9e6edfda", | |
| "size_bytes": 1764 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "a94390b062b403710c0dac1d4d5287f4b1108ace837bbffaa03d66a286778267", | |
| "size_bytes": 899 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "8b4d21a1e70ccbc8849e5e5e6dd32f3acfb2e2060739475909edc6e9b27c7165", | |
| "size_bytes": 7594 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "8561e515156fbebcb6ab670b19432fb7b725fb66e452e017fe7d1e8dd28584ef", | |
| "size_bytes": 208244 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "303aba891d66ab63908a7b3cc9163bcb835fdf8b9f6301c73216f3f1eb3992dd", | |
| "size_bytes": 244 | |
| }, | |
| { | |
| "path": "model-00001-of-00061.safetensors", | |
| "sha256": "76c7d5e3f842223f9a7c62dc5c7cca368cb66d25361c92abcfe3b0e36dca84d7", | |
| "size_bytes": 4668543279 | |
| }, | |
| { | |
| "path": "model-00002-of-00061.safetensors", | |
| "sha256": "fe4be3cc801e8dd66f3ebb6fea3436d63377119891cd5c937934a289b70bec33", | |
| "size_bytes": 5342914796 | |
| }, | |
| { | |
| "path": "model-00003-of-00061.safetensors", | |
| "sha256": "8e6b87c3299983374954fb1590c59946503e5123e3e811709775cadca45f8e74", | |
| "size_bytes": 5342914794 | |
| }, | |
| { | |
| "path": "model-00004-of-00061.safetensors", | |
| "sha256": "bb7da5a70f9966b2e84ea9e2c413260701aa391e08c92870bc1a17aad6e9d77f", | |
| "size_bytes": 5332167186 | |
| }, | |
| { | |
| "path": "model-00005-of-00061.safetensors", | |
| "sha256": "b8ca00d6ae8deded21774fc0d10cfdde672d6e636c9fc0e3992ef5ea71a9da6d", | |
| "size_bytes": 5342914794 | |
| }, | |
| { | |
| "path": "model-00006-of-00061.safetensors", | |
| "sha256": "16177d92b911fd69084c52288c080cc393fc8ae62dd88df9d1800d29c6932141", | |
| "size_bytes": 5342914752 | |
| }, | |
| { | |
| "path": "model-00007-of-00061.safetensors", | |
| "sha256": "da4220b4a4832f8d2287462a31db65170df577b29e564b1a828602de9c5c285f", | |
| "size_bytes": 5342914798 | |
| }, | |
| { | |
| "path": "model-00008-of-00061.safetensors", | |
| "sha256": "bcb798697b7623bcf9fbeb4df604b7456bc83dabf52886d37a62c35b2f82e68f", | |
| "size_bytes": 5332167196 | |
| }, | |
| { | |
| "path": "model-00009-of-00061.safetensors", | |
| "sha256": "f7dc1d5e32d92968de2008fa13360d04403a4bdc4f8f40e4d1973734a84c38dd", | |
| "size_bytes": 5342914786 | |
| }, | |
| { | |
| "path": "model-00010-of-00061.safetensors", | |
| "sha256": "a5c7daf858f6db72de62116ed4d4b2e6c3e2904900f58702f7d2c998718dfa63", | |
| "size_bytes": 5342914798 | |
| }, | |
| { | |
| "path": "model-00011-of-00061.safetensors", | |
| "sha256": "60f1849e449de83dbeb33d6970d782f8b8f07007879fe4d5bdb3c7fb5a9819dd", | |
| "size_bytes": 5342914818 | |
| }, | |
| { | |
| "path": "model-00012-of-00061.safetensors", | |
| "sha256": "92fd184f4498104a4b7f97f0558ceba608b799d8d4a6e75f0e01bd85528e5f34", | |
| "size_bytes": 5332167224 | |
| }, | |
| { | |
| "path": "model-00013-of-00061.safetensors", | |
| "sha256": "4d3755151ef8cfb900825a15a862ad0456c59ab39ae36a57486f6cc5e61d1587", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00014-of-00061.safetensors", | |
| "sha256": "bbf3232e38d4593e36236c561fb73a6394af24fb61fd3b0ff41090a1d0a9182b", | |
| "size_bytes": 5342914823 | |
| }, | |
| { | |
| "path": "model-00015-of-00061.safetensors", | |
| "sha256": "ac8c50b71120c62943d94e573a1e2dfbca1d7acc2e31f36fb2b7c8448dac3025", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00016-of-00061.safetensors", | |
| "sha256": "3eb1ddccc623370821ab66dc3becc47215704659442a187e1062af01a4a1c05c", | |
| "size_bytes": 5332167230 | |
| }, | |
| { | |
| "path": "model-00017-of-00061.safetensors", | |
| "sha256": "eb327694e9e9081f2347175afb4f5196cda7e7b309dff6645af4a56f2af7f30f", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00018-of-00061.safetensors", | |
| "sha256": "4646e207687588298101d539eb5b206c218a5e20f33fdba330defa5a9183da8f", | |
| "size_bytes": 5342914845 | |
| }, | |
| { | |
| "path": "model-00019-of-00061.safetensors", | |
| "sha256": "f16510d1121f3803507b4f21f329461ed30ec3f870786c2cda9461cf3b050472", | |
| "size_bytes": 5342914795 | |
| }, | |
| { | |
| "path": "model-00020-of-00061.safetensors", | |
| "sha256": "f6b742c6c278315f7d6c4528f42a7bee0b5d0a528113f7abefddd81fe9f13acf", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00021-of-00061.safetensors", | |
| "sha256": "a71eb88125b57cd93d82e177047c35305eda4b98f31e433d586c08615fde905b", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00022-of-00061.safetensors", | |
| "sha256": "b8e4a4b9e91a47556cb0f7e035fafe4ff5d3778b7ea7bf3af38f90c871fe6761", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00023-of-00061.safetensors", | |
| "sha256": "1e15e1e91c5010c70c73277740a6b7dbae1136d71c6e49c6e2ffac3383f0f043", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00024-of-00061.safetensors", | |
| "sha256": "daae56fa7dafa5357a31d7628c5233e5179f508cdb8e9f0203937262b3ea3c8b", | |
| "size_bytes": 5332167226 | |
| }, | |
| { | |
| "path": "model-00025-of-00061.safetensors", | |
| "sha256": "b380e25c302e8c56eb47a06d38bdd09e8332ac9089c0b6473056987e5ea19eef", | |
| "size_bytes": 5342914835 | |
| }, | |
| { | |
| "path": "model-00026-of-00061.safetensors", | |
| "sha256": "8c002ebe96dba7ac150e57060bd1b1bbaed273d38f356fe4c03f77ec30a077b1", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00027-of-00061.safetensors", | |
| "sha256": "ca121a1ae791bd98102ad94892af93ee364229d78492916d6201de725f417b20", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00028-of-00061.safetensors", | |
| "sha256": "0e7792a0c9a86922914fed806c6bb71512ccb750293296eedfd8869d502b5c52", | |
| "size_bytes": 5332167214 | |
| }, | |
| { | |
| "path": "model-00029-of-00061.safetensors", | |
| "sha256": "a16d2c028d8e2c76c29eb20797feccaee029b0f3f1f369d8c1dc317286e40cde", | |
| "size_bytes": 5342914845 | |
| }, | |
| { | |
| "path": "model-00030-of-00061.safetensors", | |
| "sha256": "35aebc2f92964904dc36489cb3406a7eb1fbf347d9a429641efe867c50d3f59b", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00031-of-00061.safetensors", | |
| "sha256": "a5a43654f7c6ac3b7203b03007b08a354e56e39f2bb1b15ed2fe7311b90c1ba6", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00032-of-00061.safetensors", | |
| "sha256": "0a8074564354412b509b10eca9d3cada3b14037baefaa99e4c272af73354c242", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00033-of-00061.safetensors", | |
| "sha256": "307ac3b9bae1343f7dc62459a56d9c748056df40b0ade3f32affe209b6f3624b", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00034-of-00061.safetensors", | |
| "sha256": "afded49fa61f2cf6a7e68ab4abd349e662d31123da6435972bb7a5e3ce9c4ee7", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00035-of-00061.safetensors", | |
| "sha256": "b0eb3fdee99cad031f645b293387d947f7a5b8a9523d8e8c69618a238fcc33a1", | |
| "size_bytes": 5342914837 | |
| }, | |
| { | |
| "path": "model-00036-of-00061.safetensors", | |
| "sha256": "1dc8b87481f4c097ea5a9557f419338f9dcaa75f0e0f59072a2d6c3416f42573", | |
| "size_bytes": 5332167236 | |
| }, | |
| { | |
| "path": "model-00037-of-00061.safetensors", | |
| "sha256": "d56b25f8fed3d329b0abffed5f3f8abc3f93166ceb38ae2decdde1390edadb42", | |
| "size_bytes": 5342914845 | |
| }, | |
| { | |
| "path": "model-00038-of-00061.safetensors", | |
| "sha256": "bcf3b991339a17716cefaaf773d5976eae8867f093424151b739cb75c277e419", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00039-of-00061.safetensors", | |
| "sha256": "8c789a93d6e7bdce3fda6f178d8347e9808026af5f7a63aa05fad0a4d2f10055", | |
| "size_bytes": 5342914845 | |
| }, | |
| { | |
| "path": "model-00040-of-00061.safetensors", | |
| "sha256": "d5c6b8a0fa3dd44f34dbf0e17d19c7f4195b930851b49610d7ca5ef05d1bf1cc", | |
| "size_bytes": 5332167216 | |
| }, | |
| { | |
| "path": "model-00041-of-00061.safetensors", | |
| "sha256": "fdb6704b0f8c4c9168e023cb6033cf8b853e24d35999213d9f0ec87c0946cc63", | |
| "size_bytes": 5342914759 | |
| }, | |
| { | |
| "path": "model-00042-of-00061.safetensors", | |
| "sha256": "3160e6c563cdfd20dea412d8e47415a7bb89b6aeb4898bfbd18f5c08360d80e0", | |
| "size_bytes": 5342914793 | |
| }, | |
| { | |
| "path": "model-00043-of-00061.safetensors", | |
| "sha256": "4547a3f53c0807032d6f176ada685de5feeff0f172cc1a6dffd125a520f6da09", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00044-of-00061.safetensors", | |
| "sha256": "b14504edab414e09b14d7fdda6bf13083b633bccec3096d4d86a7761ea66a127", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00045-of-00061.safetensors", | |
| "sha256": "322ce1fa18486a14adb872610cb334245d763ebc86760325fdf83519b0104f86", | |
| "size_bytes": 5342914845 | |
| }, | |
| { | |
| "path": "model-00046-of-00061.safetensors", | |
| "sha256": "7026486a4156fa55b35fa85fedf9d2f4b694f0cfd2a461123e9cefe4f2006658", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00047-of-00061.safetensors", | |
| "sha256": "0e56e302515247142a2feb19e02bee5a20633b97b95dee70742f3c13ea98d9b8", | |
| "size_bytes": 5342914805 | |
| }, | |
| { | |
| "path": "model-00048-of-00061.safetensors", | |
| "sha256": "cecde72cdea7bfec635f1777bc72dca1a22a85008cdd5de01bd0399a2047ff6c", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00049-of-00061.safetensors", | |
| "sha256": "1115f0604d5d9227266f60fa2a91bb3be3dfa10a909173b11cf38106858a18d8", | |
| "size_bytes": 5342914783 | |
| }, | |
| { | |
| "path": "model-00050-of-00061.safetensors", | |
| "sha256": "49459010c840e2086c8d9235cd6dc455d4b429548be46e95dbbd590bb74c9ce5", | |
| "size_bytes": 5342914801 | |
| }, | |
| { | |
| "path": "model-00051-of-00061.safetensors", | |
| "sha256": "8bd39bc70b3e303b39303f06ebcbe4b090753833f971ec31b706f2aaea567e39", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00052-of-00061.safetensors", | |
| "sha256": "55a130333164098bc1a8b50b825f14e047358c492c19e7c5f9d7f05ad5ed91c3", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00053-of-00061.safetensors", | |
| "sha256": "ee9989610c0739484ebc64246cb0cd860899c1b32bc73a0de0c74c646764f6ab", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00054-of-00061.safetensors", | |
| "sha256": "9260e48458d3dcc0e6582adbc819ccfaf41da63bbdd115b851cb3fec0ce723df", | |
| "size_bytes": 5342914839 | |
| }, | |
| { | |
| "path": "model-00055-of-00061.safetensors", | |
| "sha256": "37da4209aa327139e7a362b2bc5e9b6cfdc4b7548f333d72342823b1b9a49465", | |
| "size_bytes": 5342914835 | |
| }, | |
| { | |
| "path": "model-00056-of-00061.safetensors", | |
| "sha256": "e100fc1a536433df0caf3869edfc83339e0e6606b4c023f31ea646bc61b75699", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00057-of-00061.safetensors", | |
| "sha256": "bd487c87a5c993c3ccfcc86758510c514571124110f182252bfa8e945718a483", | |
| "size_bytes": 5342914841 | |
| }, | |
| { | |
| "path": "model-00058-of-00061.safetensors", | |
| "sha256": "aea2869cc77001e186ba0abd44b1ba80aba8a37f0079edf7dfd2c68b544a1c24", | |
| "size_bytes": 5342914837 | |
| }, | |
| { | |
| "path": "model-00059-of-00061.safetensors", | |
| "sha256": "c62926476e0a4208566049d93330bd06941ad080803eecafbe9c234cb1d6f3eb", | |
| "size_bytes": 5342914837 | |
| }, | |
| { | |
| "path": "model-00060-of-00061.safetensors", | |
| "sha256": "778cb150a91c252d84c46e9df536706b40dffe94c125619b9863c30672e92e07", | |
| "size_bytes": 5332167232 | |
| }, | |
| { | |
| "path": "model-00061-of-00061.safetensors", | |
| "sha256": "84a76f5cbe843abfd1cd03a24d2be518dd8be0c90b8f2f9cd92a3a6f547681ca", | |
| "size_bytes": 3789328052 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "3324f5cd901b06b12f6e0222faa00bde6d3c03e00148a2347141fde1d50566a5", | |
| "size_bytes": 280612 | |
| }, | |
| { | |
| "path": "mtp.safetensors", | |
| "sha256": "693134fc04009741467c2e6e7e65afdf55d5a7284d4d80fe78c1f3d786604113", | |
| "size_bytes": 13191327888 | |
| }, | |
| { | |
| "path": "mtplx_runtime.json", | |
| "sha256": "119b930ed4b470a08008aa2a51b4a83162907a85b8455f559cffa03e33236ed6", | |
| "size_bytes": 108 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523", | |
| "size_bytes": 19989325 | |
| }, | |
| { | |
| "path": "tokenizer_config.json", | |
| "sha256": "95c557768e6b88a7128befc7bfd3c7de50e5d51af9b8b33a9f4dee0e04f99679", | |
| "size_bytes": 1161 | |
| }, | |
| { | |
| "path": "vision.safetensors", | |
| "sha256": "679130e930950cdbf88494f56ffebce658b3405eebeb242ae75db9deca7657ce", | |
| "size_bytes": 912058088 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 403397928944, | |
| "main_logical_parameters": 396802360816, | |
| "main_weight_file_size_bytes": 324440690039, | |
| "measured_main_bpw": 6.541104027139504, | |
| "measured_total_bpw": 6.695761057789076, | |
| "mtp_acceptance_retention": null, | |
| "mtp_distribution": { | |
| "bf16": { | |
| "fraction": 1.0, | |
| "parameters": 6595568128 | |
| } | |
| }, | |
| "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": true, | |
| "mtp_weight_file_size_bytes": 13191327888, | |
| "plan_sha256": "575ed189d775e7f5bbd5a9ce3451a55148cd8f4f52b7adf8d8ba3390209aefd5", | |
| "profile": "agent-coding", | |
| "protected_weight_file_size_bytes": 912058088, | |
| "quantizer": "axquant", | |
| "runtime": { | |
| "ax_engine": { | |
| "decode_kernel": null, | |
| "fused_mtp": null, | |
| "kernel_evidence": "unmeasured", | |
| "model_manifest": "model-manifest.json", | |
| "preferred_group_size": 64 | |
| }, | |
| "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": "2026-09-07T03:55:33.015823Z", | |
| "kv_cache": null, | |
| "memory_policy": { | |
| "expert_stream": "required", | |
| "expert_stream_manifest": "ax_expert_stream.json", | |
| "kv_cache_precision": "runtime-default", | |
| "mtp_buffers": "preallocate-when-enabled", | |
| "prefix_cache": "runtime-managed", | |
| "unified_memory_safety_margin": "benchmark-required" | |
| }, | |
| "mtp": { | |
| "acceptance_retention": null, | |
| "detected": true, | |
| "draft_tokens": 1, | |
| "enabled_by_default": true, | |
| "head_precision": null, | |
| "measured_speedup": null, | |
| "optimized": false, | |
| "recommended_temperature_max": null, | |
| "sidecar_file": "mtp.safetensors", | |
| "verification_mode": "runtime-default" | |
| }, | |
| "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": "1.9.0", | |
| "mlx": "0.32.1", | |
| "mlx_lm": "0.31.3", | |
| "pydantic": "2.13.4", | |
| "python": "3.12.13", | |
| "safetensors": "0.8.0" | |
| }, | |
| "source_model": { | |
| "architecture": "Qwen3_5MoeForConditionalGeneration", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "ornith-ai/Ornith-1.5-397B", | |
| "revision": "8f6cc8a7aea505364523f84ccf37706e8aea0ee7" | |
| }, | |
| "target_class": "8p5bpw", | |
| "weight_distribution": { | |
| "6bit": { | |
| "fraction": 0.9771574990280152, | |
| "parameters": 394183311360 | |
| }, | |
| "8bit": { | |
| "fraction": 0.002833910434276669, | |
| "parameters": 1143193600 | |
| }, | |
| "bf16": { | |
| "fraction": 0.020008590537708194, | |
| "parameters": 8071423984 | |
| } | |
| }, | |
| "weight_file_size_bytes": 337632017927 | |
| } | |