Instructions to use AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit 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-Muse-Glimmer-30B-MLX-AXQ-4bit")
config = load_config("AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit")

# 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-Muse-Glimmer-30B-MLX-AXQ-4bit 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-Muse-Glimmer-30B-MLX-AXQ-4bit"

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-Muse-Glimmer-30B-MLX-AXQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit 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-Muse-Glimmer-30B-MLX-AXQ-4bit"

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-Muse-Glimmer-30B-MLX-AXQ-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit 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-Muse-Glimmer-30B-MLX-AXQ-4bit"

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-Muse-Glimmer-30B-MLX-AXQ-4bit" \
  --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-Muse-Glimmer-30B-MLX-AXQ-4bit

Development AXQuant (AXQ) 4bit MLX pack of meta-models/Muse-Glimmer-30B @ a4e59da52a7bc87ae7251dd5545c0dd437c44b68.

Converted via MLX-VLM muse_glimmer. Language path quantized; vision tower / adapter / projection BF16-preserved.

Not certified for AXQuant checkpoint Tier 1 on df-macstudio-m2 (2026-08-15). MLX-VLM load and generate smoke passed. Dual-suite quality vs BF16 cannot run because evaluate-quality uses the mlx-lm backend, which rejects model_type=muse_glimmer. See the evaluation record.

Claims

Claim	Status
AXQuant architecture-prior / development quant	Yes
Checkpoint Tier 1	Not certified
Dual-suite quality vs BF16	Not measured (mlx-lm backend gap)
MLX-VLM load + generate smoke	Passed on `df-macstudio-m2`
Vision / multimodal quality	Not claimed — vision BF16-protected only
Certified release	No

Source

Official: meta-models/Muse-Glimmer-30B@a4e59da52a7bc87ae7251dd5545c0dd437c44b68 (Apache-2.0)
Adapter: muse-glimmer-v1

Attribution

Base weights © Meta (Apache-2.0). Quantization by AXQuant (development).

Downloads last month: 181

Safetensors

Model size

30B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Base model

meta-models/Muse-Glimmer-30B

Quantized

(161)

this model

Collection including AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Muse-Glimmer

Collection

Muse-Glimmer 30B AXQ 4/6-bit image-text packs. • 2 items • Updated 13 days ago