Instructions to use AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit")
config = load_config("AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use AutomatosX/AX-Qwen3-VL-32B-Thinking-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-VL-32B-Thinking-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-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use AutomatosX/AX-Qwen3-VL-32B-Thinking-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-VL-32B-Thinking-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-VL-32B-Thinking-MLX-AXQ-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AutomatosX/AX-Qwen3-VL-32B-Thinking-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-VL-32B-Thinking-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-VL-32B-Thinking-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"

AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit — 6.94 BPW measured main

An AXQuant (AXQ) mixed-precision MLX checkpoint for Apple Silicon, converted directly from the BF16 source model. The language path is quantized while the vision tower are preserved at BF16 in the checkpoint (or a bound sidecar when present).

Development evidence — not a certified AXQuant release. This package has conversion and artifact-integrity records, but it does not publish measured quality, long-context, kernel-speed, or MTP-speed evidence. Do not interpret the AXQ product label as a benchmark claim.

Model details

Property	Value
Base model	Qwen/Qwen3-VL-32B-Thinking
Source revision	`7edd10ffd1196091948fb245ff63e406ccb2d4d1`
Product family	`qwen3-vl`
Source architecture	`Qwen3VLForConditionalGeneration` (dense); text path optimized
Main-model parameters	33.36B logical parameters
Quantizer	AXQuant `1.8.1`
Hub budget class	`6bit`
AXQuant base precision class	`8bit`
Planned storage-adjusted BPW	6.9379
Measured main-model BPW	6.9380
Measured total BPW	6.9380
Safetensors weight size	28.93 GB
Approximate complete download	28.94 GB
Configured maximum context	262,144 tokens; practical limits depend on unified memory
Primary MLX runtime	MLX-VLM
AX Engine native execution	Not established; no validated native manifest is included
MTP present	`False`
Vision present	`True`
Audio present	`False`

This repository contains MLX Safetensors. It does not contain PyTorch or GGUF weights.

Choosing an AXQ pack

AXQ names describe a storage-budget product class, not one uniform precision applied to every tensor. Protected tensors remain at higher precision, so the exact measured BPW is authoritative. In particular, a 6bit-named mixed plan may retain 4bit as its base precision while selecting 6-bit, 8-bit, or BF16 for other tensors to meet an approximately 6-BPW total budget. Protection floors can also raise a 4bit-named pack close to (or above) a 6bit budget on small or heavily protected models. When that collapse happens, AutomatosX does not publish a separate misleading 4bit sibling for that base.

Sibling	Intended trade-off
4bit sibling	Lower-storage AXQ budget; check its exact BPW
6bit sibling	Higher average precision near the 6-BPW budget

See the AutomatosX collections for the family catalog, or the complete index.

Download

python -m pip install -U huggingface_hub
hf download AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit --local-dir ./AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit

Allow at least 28.94 GB of free disk space. Pin the resulting Hub commit in reproducible deployments rather than relying indefinitely on main.

Run with MLX-VLM

python -m pip install -U mlx-vlm
python -m mlx_vlm.generate \
  --model AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit \
  --image ./image.png \
  --prompt "Describe this image." \
  --max-tokens 128 \
  --temperature 0.0

The protected vision tower and AXQ language decoder are loaded together by MLX-VLM. The artifact records MLX 0.32.0; runtime QA is reported separately from model-quality claims.

AX Engine status

This package does not include a validated native model-manifest.json, so AX Engine execution is not established by this release. The AX Engine fields in axquant_runtime.json describe the intended compatibility contract, not observed runtime evidence. Use the architecture-specific MLX runtime path above. The artifact records AX Engine version not recorded, but version discovery alone is not a runtime check.

Quantization layout

Main-weight precision	Parameters	Share
`6bit`	31.21B	93.55%
`8bit`	777.91M	2.33%
`bf16`	1.37B	4.12%

Quantization methods: affine, bf16.
Group sizes used by quantized assignments: 64.
MTP sidecar: not included.
Vision sidecar: not included.
Vision weights: protected BF16 in main shards.
Optimization scope: text-path.
Support tier: convertible.

BF16 sidecars, when present, are included in total download size. Their presence does not by itself establish MTP acceleration or vision-language quality.

Evidence and validation status

Check	Status
Planning evidence	`architecture_prior`
Calibration	none; the allocation is based on architecture priors
Quantizer execution	449/449 recorded module conversions succeeded; 0 fallbacks
AX Engine native manifest	not included
Quality versus BF16 or uniform baselines	Not published; no quality-retention claim
MTP acceptance and speed	not measured; no MTP speedup claim
AX Engine kernel evidence	`unmeasured`
Vision-language quality	Present, not certified; text Tier 1 does not imply VLM quality
Speech-recognition quality	Not applicable (audio disabled for this pack)
Long-context quality	262,144-token capacity is config metadata, not a validated claim
Release certification	Not certified; formal AXQuant M0-M8 gates are not closed

Modalities (capability-gated)

Text checkpoint Tier 1 does not imply vision or audio quality. Vision present=true on a pack is not a quality pass.

Modality	Claim	Supported	Reason
Vision	`present-not-certified`	`true`	vision tower BF16-protected; VL quality not certified
Audio	`not-applicable`	`false`	audio not supported on this pack

Intended use and limitations

Intended for local development and evaluation on Apple Silicon with MLX-compatible runtimes.
No minimum unified-memory figure is claimed; loadability depends on model size, context length, KV-cache policy, runtime buffers, and other processes using unified memory.
Architecture-prior allocation is not measured sensitivity. It must not be presented as measured model quality.
Vision weights are preserved at BF16, but this release does not claim validated VLM quality.
The configured context window can require substantially more memory as the KV cache grows.
AX Engine execution is not established because this package has no validated native manifest.
Upstream capabilities, limitations, biases, and responsible-use guidance still apply.

Provenance and audit files

axquant_manifest.json: package identity, byte accounting, runtime contract, software versions, and file checksums.
axquant_plan.json: per-tensor precision decisions and planning evidence.
axquant_quantizer_execution.json: conversion coverage and fallback records.
axquant_runtime.json: declared AX Engine and MLX compatibility metadata; runtime checks remain separate evidence.

All published provenance uses repository-relative paths. Local source paths are stripped before publication. The checkpoint was converted from BF16 rather than re-quantized from an OptiQ artifact. If an OptiQ repository is published separately, it uses a different quantizer and should not be assumed to have identical BPW or quality.

License

The checkpoint follows the upstream model license where applicable (often Apache License 2.0). See the Qwen/Qwen3-VL-32B-Thinking model card for license terms, model limitations, and responsible-use guidance.