Instructions to use RadixArk/Muse-Glimmer-q4-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RadixArk/Muse-Glimmer-q4-MLX 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("RadixArk/Muse-Glimmer-q4-MLX")

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

How to use RadixArk/Muse-Glimmer-q4-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RadixArk/Muse-Glimmer-q4-MLX"

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": "RadixArk/Muse-Glimmer-q4-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use RadixArk/Muse-Glimmer-q4-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "RadixArk/Muse-Glimmer-q4-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "RadixArk/Muse-Glimmer-q4-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "RadixArk/Muse-Glimmer-q4-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use RadixArk/Muse-Glimmer-q4-MLX 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 "RadixArk/Muse-Glimmer-q4-MLX"

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 RadixArk/Muse-Glimmer-q4-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RadixArk/Muse-Glimmer-q4-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RadixArk/Muse-Glimmer-q4-MLX"

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 "RadixArk/Muse-Glimmer-q4-MLX" \
  --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"

Muse-Glimmer-q4-MLX

Commit History

Sync chat template with meta-models/Muse-Glimmer-30B (fixes duplicate reasoning effort) (#1)

4a4f54a

Jiminator commited on 4 days ago

Card: remove private-distribution notice ahead of public release

a35f715
verified

Jiminator commited on 10 days ago

Add processor_config.json (required by the muse_glimmer processor path; smoke-verified on sglang#34262)

0ebf916
verified

Jiminator commited on 10 days ago

Muse Glimmer convention: model_type muse_glimmer, architectures MuseGlimmerForConditionalGeneration, rename shipped model code, remove Onyx naming

710ac70
verified

Jiminator commited on 10 days ago

docs: full model card (specs, evals, perf, serving)

e0cba4c
verified

Jiminator commited on 11 days ago

Remove bytecode cache debris

e4d9843
verified

Jiminator commited on 13 days ago

Add files using upload-large-folder tool

cd38a1c
verified

Jiminator commited on 13 days ago

initial commit

ad101fe
verified

Jiminator commited on 13 days ago

Commit History

Sync chat template with meta-models/Muse-Glimmer-30B (fixes duplicate reasoning effort) (#1) 4a4f54a

Card: remove private-distribution notice ahead of public release a35f715 verified

Add processor_config.json (required by the muse_glimmer processor path; smoke-verified on sglang#34262) 0ebf916 verified

Muse Glimmer convention: model_type muse_glimmer, architectures MuseGlimmerForConditionalGeneration, rename shipped model code, remove Onyx naming 710ac70 verified

docs: full model card (specs, evals, perf, serving) e0cba4c verified

Remove bytecode cache debris e4d9843 verified

Add files using upload-large-folder tool cd38a1c verified

initial commit ad101fe verified

Sync chat template with meta-models/Muse-Glimmer-30B (fixes duplicate reasoning effort) (#1)

4a4f54a

Card: remove private-distribution notice ahead of public release

a35f715
verified

Add processor_config.json (required by the muse_glimmer processor path; smoke-verified on sglang#34262)

0ebf916
verified

Muse Glimmer convention: model_type muse_glimmer, architectures MuseGlimmerForConditionalGeneration, rename shipped model code, remove Onyx naming

710ac70
verified

docs: full model card (specs, evals, perf, serving)

e0cba4c
verified

Remove bytecode cache debris

e4d9843
verified

Add files using upload-large-folder tool

cd38a1c
verified

initial commit

ad101fe
verified