Text Generation
MLX
Safetensors
qwen3_5
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3.8
4bit
4-bit precision
vision
conversational
Instructions to use AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit 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-4bit 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-4bit") 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-4bit 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-4bit"
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-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit 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-4bit"
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-4bit" # 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-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit 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-4bit"
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-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit 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-4bit"
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-4bit" \ --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": "2026-08-14T17:20:59.914972Z", | |
| "effective_bpw": 5.06658845614543, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "e8d287de4a2c9c792b1fd406e8961b31e22889e91ca485280c959d2826c06c55", | |
| "size_bytes": 8442 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "19c649a1f5ced52d596857349a3b7e2d9e1b87c222975b05b4b3caf3ac393f84", | |
| "size_bytes": 1077755 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "3506f519d9d89da003aa7fd360266d6e28582a8d75e4bfaf57c7dd218b7af473", | |
| "size_bytes": 130100 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "4b5c19952b2f89be218662c58e11ed93c3cc481b96e0b943c7d661dd659bccdf", | |
| "size_bytes": 1628 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "7d994ab3260a8f59e2b5770c6fde5f23d01bbb63e6e24890b78ae46df975e4cc", | |
| "size_bytes": 887 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041", | |
| "size_bytes": 8952 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "9dc38f455eb4972c1d64f4c5e66c7934689f3caf8710e80428525ce09814eabb", | |
| "size_bytes": 132195 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e", | |
| "size_bytes": 202 | |
| }, | |
| { | |
| "path": "model-00001-of-00004.safetensors", | |
| "sha256": "9d973f0eeccf9c7954963be2a27918cd13d47bf5129702d8e94d2ad2dc08b8dc", | |
| "size_bytes": 5367839117 | |
| }, | |
| { | |
| "path": "model-00002-of-00004.safetensors", | |
| "sha256": "9d0b79483965b3aa43955b25cd52fc70301710ce9fe90222b1be4ad41ef09c22", | |
| "size_bytes": 5353499253 | |
| }, | |
| { | |
| "path": "model-00003-of-00004.safetensors", | |
| "sha256": "e6b080adf4bfbcdcffd8aee6c778ddf5a20f93b99ffa50d503ed77b05007509f", | |
| "size_bytes": 4332242476 | |
| }, | |
| { | |
| "path": "model-00004-of-00004.safetensors", | |
| "sha256": "e22b409edeff75e4c88ca5ece0ccb469fb71910df0e63987e1982f6be9357162", | |
| "size_bytes": 1350861149 | |
| }, | |
| { | |
| "path": "model-manifest.json", | |
| "sha256": "07b0c23628762b44647f321e3437719be94ad0b493d7a7e0df6d6c31114d2fb8", | |
| "size_bytes": 434304 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "29c882cf47ac703b18da5c597f754aa9b57aa4232ae3db56a08f5d1746837a0d", | |
| "size_bytes": 189789 | |
| }, | |
| { | |
| "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": 27356728560, | |
| "main_logical_parameters": 27356728560, | |
| "main_weight_file_size_bytes": 17325939315, | |
| "measured_main_bpw": 5.06666994980777, | |
| "measured_total_bpw": 5.06666994980777, | |
| "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": "cbdcb681d80370233e5b88ac948d36d7688d210f0e8460d078c06a9c87b5260f", | |
| "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": 64 | |
| }, | |
| "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": "2026-08-14T17:20:35.354015Z", | |
| "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": "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": "4bit", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.8901121384668957, | |
| "parameters": 24350556160 | |
| }, | |
| "8bit": { | |
| "fraction": 0.09294959353136924, | |
| "parameters": 2542796800 | |
| }, | |
| "bf16": { | |
| "fraction": 0.016938268001735073, | |
| "parameters": 463375600 | |
| } | |
| }, | |
| "weight_file_size_bytes": 17325939315 | |
| } | |