Text Generation
MLX
Safetensors
qwen3_5
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3.6
6bit
6-bit
vision
conversational
4-bit precision
Instructions to use AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit 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-Qwen3.6-27B-MLX-AXQ-6bit") 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-Qwen3.6-27B-MLX-AXQ-6bit 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-Qwen3.6-27B-MLX-AXQ-6bit"
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-Qwen3.6-27B-MLX-AXQ-6bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit 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-Qwen3.6-27B-MLX-AXQ-6bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit" # 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-Qwen3.6-27B-MLX-AXQ-6bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit 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-Qwen3.6-27B-MLX-AXQ-6bit"
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-Qwen3.6-27B-MLX-AXQ-6bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit 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-Qwen3.6-27B-MLX-AXQ-6bit"
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-Qwen3.6-27B-MLX-AXQ-6bit" \ --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": "1.5.1", | |
| "calibration": { | |
| "backend": "axquant-mlx-isolated-probe-v4", | |
| "dataset_id": "calibration-agent-coding-v1.jsonl", | |
| "dataset_sha256": "1eb549ff8fc2565559fbea37ef82b08629b5dc12f7bace69af579e35fc62226f", | |
| "domains": [ | |
| "coding", | |
| "json", | |
| "long-context", | |
| "multilingual", | |
| "tool" | |
| ], | |
| "metadata": { | |
| "base_inventory_sha256": "ba2a8442c989f86d336e31a74f784bbd714884d1a52b129fac416ba19354711e", | |
| "base_probe_backend": "axquant-mlx-isolated-probe-v3", | |
| "base_sensitivity_sha256": "58f2b52dba9f0585d14c7d230307aafeabe597e03de8e48663ed959733459d9e", | |
| "cache_key_sha256": "ca8b598b0cb0cdcf967f84e29693365afb88d6bf596cbe9f9aa82857fb5b9cf3", | |
| "calibration_manifest_sha256": "0f3d203c48ebea236f8e93a2773d0714585065f89478583aa91c66525f7e1895", | |
| "calibration_random_seed": 20260728, | |
| "candidate_methods": "dwq", | |
| "capture_points": "output,hidden", | |
| "domain_provenance": "sample-records", | |
| "long_context_min_tokens": 1024, | |
| "measured_tokens_per_candidate": 8192, | |
| "metric_positions_per_sample": 8, | |
| "module_group_probing": false, | |
| "normalization": "quality means over fixed token positions; memory and prefill latency are candidate/reference ratios after warmup; method refinements with identical bit/group/packing reuse the base affine hardware-cost control", | |
| "packed_replay_sequences": 4, | |
| "packing": "ordered token concatenation bounded by cache sequence length", | |
| "refinement_probe_backend": "axquant-mlx-isolated-probe-v4", | |
| "replay_batch_size": 1, | |
| "replay_batches": 4, | |
| "sample_order_sha256": "8bfc97c9573a6e24a1234dcb23e8412b4cc1c60c87db5e3c1f8d39997d44a90e", | |
| "target_tensor_count": 8, | |
| "token_budget_per_candidate": 8192, | |
| "tokenizer_sha256": "b2abe9b8739ed57acd7086c493006e91889d6311b2a02bbb2f613292b4827768", | |
| "warmup_replays": 1 | |
| }, | |
| "reference": "measured-forward-probe-refinement", | |
| "samples": 144, | |
| "sequence_length": 2048 | |
| }, | |
| "created_at": "2026-08-08T01:50:51.714195Z", | |
| "effective_bpw": 5.717093964011515, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "66b6dfd71c1f51d1a6005659ab533160ee16855fafe5ab02a0334ac2de3d035b", | |
| "size_bytes": 8514 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "08a9b19828959210b65670dde4c90d58280f5913ae7106a5befa252b189d70b4", | |
| "size_bytes": 1191514 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "195331d408615737c0c2322effa099ce0d534f95875a35c052370270460de28a", | |
| "size_bytes": 127774 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "37d261d9fe950fcd4a4511304475f606893d30c2f4dca11009dbca5d8010b4bb", | |
| "size_bytes": 1676 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "2e9be8e2ae2f3e0c6ca7c9d2c376f490b1421149b21a72e3eadf51afdfa2a720", | |
| "size_bytes": 1065 | |
| }, | |
| { | |
| "path": "calibration_manifest.json", | |
| "sha256": "89496ffd28d1c782c3ded857cdb195c0336a21645cc33fef1c9586dab793fb0a", | |
| "size_bytes": 703 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259", | |
| "size_bytes": 7764 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "bb0a3c385852ec6366d704f9424f5e3d011fc0d253ea86dbd7cfc37cb396084c", | |
| "size_bytes": 129341 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e", | |
| "size_bytes": 202 | |
| }, | |
| { | |
| "path": "model-00001-of-00004.safetensors", | |
| "sha256": "64495f79b5d6411c9d2956e261aff4995462152510ed1ee476f4dc6000886d10", | |
| "size_bytes": 5344738984 | |
| }, | |
| { | |
| "path": "model-00002-of-00004.safetensors", | |
| "sha256": "40a4d3d9e18a3e88144534f515b1aa362042d637ed6550bc706233c5612976b7", | |
| "size_bytes": 5328093538 | |
| }, | |
| { | |
| "path": "model-00003-of-00004.safetensors", | |
| "sha256": "dfa8e730718a1818633c9b60fd294c31db5bd1d749cb75f89d2a4f746faf6437", | |
| "size_bytes": 5326527020 | |
| }, | |
| { | |
| "path": "model-00004-of-00004.safetensors", | |
| "sha256": "96a459e4da05ba4943d6b7e9f67e860482b06d514cf46b6cda55c57193a22d80", | |
| "size_bytes": 2932772395 | |
| }, | |
| { | |
| "path": "model-manifest.json", | |
| "sha256": "c3e0c4b733b831569033260f879da482fbaea28d924d9b51836a5acc715b020d", | |
| "size_bytes": 432810 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "a17a68c25b829b45f3f0d54510f7a549116a7ad77966225853407c8aecbb5fb5", | |
| "size_bytes": 187511 | |
| }, | |
| { | |
| "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": "32396b51006e25e7aea94d287b5d81d4044fa910a40aa558db55a9f273895c00", | |
| "size_bytes": 921497320 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 27781427952, | |
| "main_logical_parameters": 27356728560, | |
| "main_weight_file_size_bytes": 19853629257, | |
| "measured_main_bpw": 5.805848959887475, | |
| "measured_total_bpw": 5.717093964011515, | |
| "mtp_acceptance_retention": null, | |
| "mtp_distribution": {}, | |
| "mtp_measured_speedup": null, | |
| "mtp_policy": { | |
| "candidate_bits": [ | |
| 8, | |
| 16 | |
| ], | |
| "min_bits": 8, | |
| "mode": "disabled", | |
| "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": "ef27ce452b6ac5c0194ce3b68aa3042f0626a652bf13cfb431f7a7608549d2a2", | |
| "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": "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": "2026-08-08T01:50:44.677562Z", | |
| "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": "6.13.5", | |
| "axquant": "1.5.1", | |
| "mlx": "0.32.0", | |
| "mlx_lm": "0.31.3", | |
| "pydantic": "2.13.4", | |
| "python": "3.13.14", | |
| "safetensors": "0.8.0" | |
| }, | |
| "source_model": { | |
| "architecture": "Qwen3_5ForConditionalGeneration", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "revision": "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9" | |
| }, | |
| "target_class": "6bit", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.7479194646113991, | |
| "parameters": 20778270720 | |
| }, | |
| "6bit": { | |
| "fraction": 0.11515979976002927, | |
| "parameters": 3199303680 | |
| }, | |
| "8bit": { | |
| "fraction": 0.045773174877731714, | |
| "parameters": 1271644160 | |
| }, | |
| "bf16": { | |
| "fraction": 0.09114756075083984, | |
| "parameters": 2532209392 | |
| } | |
| }, | |
| "weight_file_size_bytes": 19853629257 | |
| } | |