Text Generation
MLX
Safetensors
qwen3_5_moe
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3.5-moe
MXFP4
vision
conversational
4-bit precision
Instructions to use AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4") 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4"
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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4" # 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4"
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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AutomatosX/AX-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4"
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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4" \ --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-Holo-3.1-35B-A3B-MLX-AXQ-MXFP4 from Hcompany/Holo-3.1-35B-A3B@2bdb92851a8cd9d72cdd891fdf38cfcc7fefae2c
23aa374 verified | { | |
| "axquant_version": "1.8.1", | |
| "calibration": null, | |
| "created_at": "2026-08-16T00:43:34.196666Z", | |
| "effective_bpw": 5.352430434278534, | |
| "files": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "85290d02f447f99829d32bab5c3f24bf3526aa8d89e4313afe73045c73351470", | |
| "size_bytes": 8100 | |
| }, | |
| { | |
| "path": "axquant_plan.json", | |
| "sha256": "a3492ca807b92ce32c7e1d1f8a82116c573626007d53ed23ecd166477eafd108", | |
| "size_bytes": 941079 | |
| }, | |
| { | |
| "path": "axquant_quantizer_execution.json", | |
| "sha256": "221f97318717c8fb9cba1ff9042a3d977ca4e60555b7609f9cdc2ae7012426d8", | |
| "size_bytes": 124996 | |
| }, | |
| { | |
| "path": "axquant_runtime.json", | |
| "sha256": "656c8333450c0bddd97833007722d293b9e7364851b3de8f171f70707ff0ccce", | |
| "size_bytes": 1628 | |
| }, | |
| { | |
| "path": "axquant_vision_sidecar_manifest.json", | |
| "sha256": "0c6c5bce0b3fe6a093ad66fcda815a27a2ef60fd085665f9851170beea8979c7", | |
| "size_bytes": 1077 | |
| }, | |
| { | |
| "path": "chat_template.jinja", | |
| "sha256": "e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259", | |
| "size_bytes": 7764 | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "b2491118a3c5c3a3c7d90b9098c941207df63eed33423e33eb61e971d8300cb4", | |
| "size_bytes": 138645 | |
| }, | |
| { | |
| "path": "generation_config.json", | |
| "sha256": "a219dff6ed1d52d8a88fe50026de36ebcbcb913cbac0e70fdfaecf380949d7f1", | |
| "size_bytes": 213 | |
| }, | |
| { | |
| "path": "model-00001-of-00004.safetensors", | |
| "sha256": "68286822a861daf04d2ad4a59728e6da114dc6741c3b63fbcb19973fcded6780", | |
| "size_bytes": 5350198081 | |
| }, | |
| { | |
| "path": "model-00002-of-00004.safetensors", | |
| "sha256": "0a8f7e685e6f389bbe44fc33c1adac47f57b969163a7c40be52f4c0614be35e6", | |
| "size_bytes": 5366938358 | |
| }, | |
| { | |
| "path": "model-00003-of-00004.safetensors", | |
| "sha256": "aa080d7c4707434ba460260bbf44c4e1f7787d3ce53bffafa90eb43b6eaa61a4", | |
| "size_bytes": 5366938378 | |
| }, | |
| { | |
| "path": "model-00004-of-00004.safetensors", | |
| "sha256": "d546d08caede60969fb26c2b018b9ea6a90d452dde5ee8acff39449031c94ada", | |
| "size_bytes": 4412094706 | |
| }, | |
| { | |
| "path": "model.safetensors.index.json", | |
| "sha256": "3fee494e6ed9046e9f95c5c1381e88e1e3e00e0bd902a152aa226744c9e87059", | |
| "size_bytes": 140457 | |
| }, | |
| { | |
| "path": "tokenizer.json", | |
| "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523", | |
| "size_bytes": 19989325 | |
| }, | |
| { | |
| "path": "tokenizer_config.json", | |
| "sha256": "95c557768e6b88a7128befc7bfd3c7de50e5d51af9b8b33a9f4dee0e04f99679", | |
| "size_bytes": 1161 | |
| }, | |
| { | |
| "path": "vision.safetensors", | |
| "sha256": "5c2faeebf7966376b30d98d0b623eb78b4d7c9ef53d7065fc8e47d9bb4abb9d7", | |
| "size_bytes": 893179624 | |
| } | |
| ], | |
| "format": "mlx", | |
| "logical_parameters": 35107181936, | |
| "main_logical_parameters": 35107181936, | |
| "main_weight_file_size_bytes": 21389349147, | |
| "measured_main_bpw": 4.874068032231706, | |
| "measured_total_bpw": 4.874068032231706, | |
| "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": "d1e24ddf50d1df3471184992c136e6f0cbf8dfc2aac2826061e147a41a85e010", | |
| "profile": "agent-coding", | |
| "protected_weight_file_size_bytes": 893179624, | |
| "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": "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": "2026-08-16T00:43:05.941156Z", | |
| "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": null, | |
| "axquant": "1.8.1", | |
| "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_5MoeForConditionalGeneration", | |
| "format": "mlx", | |
| "local_path": null, | |
| "model_id": "Hcompany/Holo-3.1-35B-A3B", | |
| "revision": "2bdb92851a8cd9d72cdd891fdf38cfcc7fefae2c" | |
| }, | |
| "target_class": "8bit", | |
| "weight_distribution": { | |
| "4bit": { | |
| "fraction": 0.957675235263577, | |
| "parameters": 33621278720 | |
| }, | |
| "8bit": { | |
| "fraction": 0.015085597042949166, | |
| "parameters": 529612800 | |
| }, | |
| "bf16": { | |
| "fraction": 0.027239167693473853, | |
| "parameters": 956290416 | |
| } | |
| }, | |
| "weight_file_size_bytes": 21389349147 | |
| } | |