Text Generation
MLX
Safetensors
qwen3_5
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3.8
6bit
6-bit
mtp
vision
conversational
4-bit precision
Instructions to use AutomatosX/AX-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-MLX-AXQ-6bit-MTP"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/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-Qwen3.8-27B-MLX-AXQ-6bit-MTP" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-MLX-AXQ-6bit-MTP", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-MLX-AXQ-6bit-MTP
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-Qwen3.8-27B-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-Qwen3.8-27B-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-Qwen3.8-27B-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"
| { | |
| "axquant_version": "1.6.2", | |
| "calibration": null, | |
| "created_at": "2026-08-14T15:33:54.231561Z", | |
| "effective_bpw": 5.999995847585653, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "88cd91d04b02d809eb48e01f4ac751ed74ed2bc113614a91ea14703ba0afa24c", | |
| "size_bytes": 8842 | |
| }, | |
| { | |
| "path": "axquant_mtp_sidecar_manifest.json", | |
| "sha256": "2f3e71df1c5b08c6f5af9b6b0b2e79c51e80ecb2d1ee36d0355ed9b6cfd10be4", | |
| "size_bytes": 880 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "9a636a6c9bcbf29ec3c652a65b7ff6832ff9d654e9d29fdeedd0932c909d5d62", | |
| "size_bytes": 1136252 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "5385db149a32005a6b56fb8823fc9fd047f15f1e6ca2d611b1f3f9757712fa69", | |
| "size_bytes": 129880 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "3a2656bcf22f31feb788a00ddb8d9e853e741a121b273c6cf94fdc228274abab", | |
| "size_bytes": 1676 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "d4196a4d77b0e7a5ec743f22334625c3397f2a9d13986c76f3b976eeea967f7d", | |
| "size_bytes": 887 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041", | |
| "size_bytes": 8952 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "850c0bf06e1baa0b250544b9b0ba4b3f8ea1716fb64937f7791ad421450f8054", | |
| "size_bytes": 131989 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e", | |
| "size_bytes": 202 | |
| }, | |
| { | |
| "path": "model-00001-of-00004.safetensors", | |
| "sha256": "d45beafeb00e3d6b172a4e6aabc2359691f0b98a06559d68a3d0e48043305b01", | |
| "size_bytes": 5367227318 | |
| }, | |
| { | |
| "path": "model-00002-of-00004.safetensors", | |
| "sha256": "6fcb8ad0ca0b812b45bada6565a531da9c2a27810d57fe1d1f551b475491b514", | |
| "size_bytes": 5331903686 | |
| }, | |
| { | |
| "path": "model-00003-of-00004.safetensors", | |
| "sha256": "cff8ff8f81cee61fcca46e0e091c3f62ad4b14c614b5900c731b2de90c8ed9dc", | |
| "size_bytes": 5349212082 | |
| }, | |
| { | |
| "path": "model-00004-of-00004.safetensors", | |
| "sha256": "7363f3f12faf0bcecb79d308ff3c6ff5787daa70a9a0431a72ceb098c3c97678", | |
| "size_bytes": 3017096808 | |
| }, | |
| { | |
| "path": "model-manifest.json", | |
| "sha256": "e3699d9af5e0585d3e65b1acbed3cf1697141c5da48d0be976a668381b00329a", | |
| "size_bytes": 434190 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "c9c5b1336f1c552f149e95c818a7431f65971292d12d4f2ab5ff37689654328d", | |
| "size_bytes": 189635 | |
| }, | |
| { | |
| "path": "mtp.safetensors", | |
| "sha256": "914bef4ec6fcfde83925f9c138559253db030d9138b0a375623d6fdc06ebe898", | |
| "size_bytes": 849400520 | |
| }, | |
| { | |
| "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": "d0d927c489250588557d5761dcd47ca267ef64c95f7e7d58dd6a0cccf54ac68f", | |
| "size_bytes": 921497320 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 27781427952, | |
| "main_logical_parameters": 27356728560, | |
| "main_weight_file_size_bytes": 19986937214, | |
| "measured_main_bpw": 5.844832555958218, | |
| "measured_total_bpw": 6.000076819665414, | |
| "mtp_acceptance_retention": null, | |
| "mtp_distribution": { | |
| "bf16": { | |
| "fraction": 1.0, | |
| "parameters": 424699392 | |
| } | |
| }, | |
| "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": 849400520, | |
| "plan_sha256": "8b35c3932af38b2ee30de1829b711554c7b67532ad30ced378e66ef6269e4c81", | |
| "profile": "agent-coding", | |
| "protected_weight_file_size_bytes": 921497320, | |
| "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": "2026-08-14T15:33:25.166760Z", | |
| "kv_cache": null, | |
| "memory_policy": { | |
| "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": "6.16.1", | |
| "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": "Qwen3_5ForConditionalGeneration", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "Qwen/Qwen3.8-27B", | |
| "revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0" | |
| }, | |
| "target_class": "6bit", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.8759593280102825, | |
| "parameters": 24335400960 | |
| }, | |
| "6bit": { | |
| "fraction": 0.0005455155158397454, | |
| "parameters": 15155200 | |
| }, | |
| "8bit": { | |
| "fraction": 0.04576432868017755, | |
| "parameters": 1271398400 | |
| }, | |
| "bf16": { | |
| "fraction": 0.07773082779370015, | |
| "parameters": 2159473392 | |
| } | |
| }, | |
| "weight_file_size_bytes": 20836337734 | |
| } | |