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
LM Studio

Pi new

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

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"}
     ]
   }'

A newer version of this model is available: YOYO-AI/YOYO-O1-32B-V4-preview4

bobig/QwQ-Coder-instruct-mlx-4Bit

This is pretty good. QwQ brains and memory + Qwen code instruct

Now in delicious MLX, eat it or wear it

32k context is solid in QwQ: https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87

Test Prompt: Write a quick sort in C++

The Model bobig/QwQ-Coder-instruct-mlx-4Bit was converted to MLX format from YOYO-AI/QwQ-Coder-instruct using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bobig/QwQ-Coder-instruct-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 5

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/QwQ-Coder-instruct-mlx-4Bit

Base model

YOYO-AI/QwQ-Coder-instruct

Quantized

(4)

this model