Instructions to use michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 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("michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7")

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 michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"

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": "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 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 "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"

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 michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7"

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 "michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7" \
  --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"

This model was generated using DWQ quantization to bring the quality of the 4bit quantization closer to 8bit without increasing in size. This was done using mlx-lm version 0.26.3, using --bits 4 --learning-rate 1e-7 --batch-size 1 --group-size 16.

Downloads last month: 7

Safetensors

Model size

1B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for michaellin/Qwen2.5-Coder-7B-4bit-mlx-dwq-lr1e-7

Base model

Qwen/Qwen2.5-7B

Finetuned

mlx-community/Qwen2.5-Coder-7B-8bit

Quantized

(1)

this model