Instructions to use AutomatosX/AX-Qwen3-VL-4B-Instruct-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-4B-Instruct-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-4B-Instruct-MLX-AXQ-6bit")
config = load_config("AutomatosX/AX-Qwen3-VL-4B-Instruct-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-4B-Instruct-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-4B-Instruct-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-VL-4B-Instruct-MLX-AXQ-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use AutomatosX/AX-Qwen3-VL-4B-Instruct-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-4B-Instruct-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-4B-Instruct-MLX-AXQ-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AutomatosX/AX-Qwen3-VL-4B-Instruct-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-4B-Instruct-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-4B-Instruct-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-4B-Instruct-MLX-AXQ-6bit

Research development artifact. Base affine6 packing with higher-precision protection, not MXFP6 or uniformly six-bit storage. No quality certificate is issued.

Property	Value
Source	Qwen/Qwen3-VL-4B-Instruct
Immutable source revision	`ebb281ec70b05090aa6165b016eac8ec08e71b17`
Complete storage	4,448,622,111 bytes
Complete measured BPW	8.019480
Manifest budget class	`8bit`
MTP	No MTP payload is advertised.

The precision distribution and exact per-module settings are recorded in axquant_manifest.json, axquant_plan.json, and config.json. Complete BPW includes protected tensors and storage overhead. File size does not establish peak runtime memory requirements. Converted from the pinned original source with existing precision protection floors.

Observed runtime evidence

The exact runtime payload passed the following scoped check on Metal. The receipt binds its runtime input files. This is a functional smoke, not a quality benchmark, MTEB evaluation, coding evaluation, long-context test or MTP acceleration result.

{
  "task": "vision",
  "runtime": "mlx-vlm",
  "version": "0.7.9",
  "mlx_version": "0.32.4",
  "cases": [
    {
      "expected": "AXQ 7319",
      "output": "AXQ 7319",
      "passed": true,
      "prompt": "Read all the text in the image. Output only the text."
    }
  ]
}

Runtime	Evidence for this artifact
MLX-VLM 0.7.9	Passed the task-specific smoke above
MLX-LM	Not separately tested
AX Engine	Not tested; architecture metadata is not execution evidence
omlx	unsupported (static only)
mtplx	unsupported (static only)

Unexercised modalities and MTP behavior remain unverified. Peer runtime-specific exports require distinct variants and their own testing. See the manifest-bound static report.

Use and provenance

python -m pip install -U huggingface_hub mlx-vlm
hf download AutomatosX/AX-Qwen3-VL-4B-Instruct-MLX-AXQ-6bit --local-dir ./AX-Qwen3-VL-4B-Instruct-MLX-AXQ-6bit

Pin the immutable Hub revision. Use the architecture-aware runtime above and preserve the source processor/template. The source license and notices are retained where supplied. The upstream repository and its license govern downstream use; no additional commercial grant or upstream benchmark/certification transfer is implied.

Downloads last month: 38

Safetensors

Model size

4B params

Tensor type

U32

BF16

MLX

Hardware compatibility

6-bit

Model tree for AutomatosX/AX-Qwen3-VL-4B-Instruct-MLX-AXQ-6bit

Base model

Qwen/Qwen3-VL-4B-Instruct

Quantized

(114)

this model

Collections including AutomatosX/AX-Qwen3-VL-4B-Instruct-MLX-AXQ-6bit