Instructions to use mlx-community/QwQ-Coder-instruct-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/QwQ-Coder-instruct-mlx-4Bit 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("mlx-community/QwQ-Coder-instruct-mlx-4Bit")

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 mlx-community/QwQ-Coder-instruct-mlx-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 "mlx-community/QwQ-Coder-instruct-mlx-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": "mlx-community/QwQ-Coder-instruct-mlx-4Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/QwQ-Coder-instruct-mlx-4Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/QwQ-Coder-instruct-mlx-4Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/QwQ-Coder-instruct-mlx-4Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/QwQ-Coder-instruct-mlx-4Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/QwQ-Coder-instruct-mlx-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 "mlx-community/QwQ-Coder-instruct-mlx-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 mlx-community/QwQ-Coder-instruct-mlx-4Bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/QwQ-Coder-instruct-mlx-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 "mlx-community/QwQ-Coder-instruct-mlx-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 "mlx-community/QwQ-Coder-instruct-mlx-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"

Is this really based on the older version of QwQ-Coder

by lael11 - opened Mar 19, 2025

Discussion

lael11

MLX Community org Mar 19, 2025

According to the model card this is based on YOYO's Qwen2.5-32 and QwQ-32B-Preview merge. He has an updated QwQ-32B [non-preview] merge, was the older version linked by accident, or is this indeed an MLX port of the older preview merge?

bobig

MLX Community org Mar 20, 2025

•

edited Mar 20, 2025

Good question, sm54 is just this guy, you know?

He tries a lot of stuff and makes some mistakes.
I tried about 20 QwQ merges. I like this one from sm54.
I like it more than Gemma3 or Exaone or DavidAu merges.
But I can't tell you for sure what is inside, I just converted his merge to MLX for the Mac bros. You get what you paid for ;-)

LMMs are moving so fast, this will be obsolete next week!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment