Text Generation
MLX
Safetensors
llama
apple-silicon
quantized
mixed-precision
axquant
axq
development
minicpm5
6bit
6-bit
conversational
4-bit precision
Instructions to use AutomatosX/AX-MiniCPM5-1B-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-MLX-AXQ-6bit"
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-MiniCPM5-1B-MLX-AXQ-6bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use AutomatosX/AX-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-MLX-AXQ-6bit
Run Hermes
hermes
- OpenClaw new
How to use AutomatosX/AX-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-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"
- MLX LM
How to use AutomatosX/AX-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-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-MiniCPM5-1B-MLX-AXQ-6bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "axquant_version": "1.0.0", | |
| "calibration": null, | |
| "created_at": "2026-08-02T18:28:19.133055Z", | |
| "effective_bpw": 7.379967222761561, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "aeef4a8e7240fc5b730327314867450a126655a604ab8172edd02e447395b10e", | |
| "size_bytes": 7340 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "ab4946c29168ce7292be60a67e92ec0f5c6c70936b23d348940ad93451f0f38a", | |
| "size_bytes": 203417 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "3f20dfbb2fad6eab77ff99d0e111363ffc3086d9a3bbf7d41418df6ff89ce5a4", | |
| "size_bytes": 41265 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "b02247f3ae6aacdb4a03c5320e3a9d19c85b71879360bc484c6515baa8e3ad0a", | |
| "size_bytes": 1643 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "7451a05cf1e28a79d97d7c0bc951028c0b1915119bf9046acd06a0e3d931f47c", | |
| "size_bytes": 9062 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "e3debd12d4d8eceeaa4ac74aae8930b86ec1b7c61f52264a36dd045f208edd89", | |
| "size_bytes": 47172 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "92afd6424501426eddcf7e1542f013d19e5987544977b4ee7bd26359bd5fd2ab", | |
| "size_bytes": 213 | |
| }, | |
| { | |
| "path": "model-manifest.json", | |
| "sha256": "7e51ebe6c2ce5c2276105322a5026eb653542f7b3b7da30aab221bd8b43c0b01", | |
| "size_bytes": 86992 | |
| }, | |
| { | |
| "path": "model.safetensors", | |
| "sha256": "548256a68c54ccdacc31faa581d2929f7233a2ac50f22074a40b98c2f05654fb", | |
| "size_bytes": 996941625 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "c147a4dff82e95025c8885867a36a676f0a74e6dfc82150f084f07fffc2972be", | |
| "size_bytes": 39286 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "3e065a558a034185fe299917b398685c1facd0169a9eea1e629eb30c171fed81", | |
| "size_bytes": 9894271 | |
| }, | |
| { | |
| "path": "tokenizer_config.json", | |
| "sha256": "b99b837295c979cc956b9e018fe710123a5547df9d4143894ba7b95a7f08c42b", | |
| "size_bytes": 460 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 1080632832, | |
| "main_logical_parameters": 1080632832, | |
| "main_weight_file_size_bytes": 996941625, | |
| "measured_main_bpw": 7.380428174886324, | |
| "measured_total_bpw": 7.380428174886324, | |
| "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": "f29387b8618976318aab0d6d246db7817c09c8bd3fa537d3d2ea62246aefed6e", | |
| "profile": "general", | |
| "protected_weight_file_size_bytes": 0, | |
| "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": "2026-08-02T18:28:18.657152Z", | |
| "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": "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": "1.0.0", | |
| "mlx": "0.32.0", | |
| "mlx_lm": "0.31.3", | |
| "pydantic": "2.13.4", | |
| "python": "3.13.14", | |
| "safetensors": "0.8.0" | |
| }, | |
| "source_model": { | |
| "architecture": "LlamaForCausalLM", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "openbmb/MiniCPM5-1B", | |
| "revision": null | |
| }, | |
| "target_class": "4bit", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.6287771645272388, | |
| "parameters": 679477248 | |
| }, | |
| "8bit": { | |
| "fraction": 0.18557659369727533, | |
| "parameters": 200540160 | |
| }, | |
| "bf16": { | |
| "fraction": 0.18564624177548586, | |
| "parameters": 200615424 | |
| } | |
| }, | |
| "weight_file_size_bytes": 996941625 | |
| } | |