Instructions to use mlx-community/Qwen3.8-27B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Qwen3.8-27B-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("mlx-community/Qwen3.8-27B-4bit")
config = load_config("mlx-community/Qwen3.8-27B-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 mlx-community/Qwen3.8-27B-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/Qwen3.8-27B-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/Qwen3.8-27B-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/Qwen3.8-27B-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/Qwen3.8-27B-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/Qwen3.8-27B-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Qwen3.8-27B-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/Qwen3.8-27B-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/Qwen3.8-27B-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"

Awesome

by tech143 - opened 4 days ago

Discussion

tech143

4 days ago

This runs so nice on my m5 max.

SeanKa

4 days ago

on m4pro is ok?

Banaxi-Tech

4 days ago

Yeah m2 pro and m2 max works too and m4 pro definitely

ziyanlee

2 days ago

which size of unified memory do you have

Turing-010

MLX Community org 2 days ago

128G，My computer is 14 inches in size but it gets too hot when running.

datagram

MLX Community org 2 days ago

128G，My computer is 14 inches in size but it gets too hot when running.

can you use zsh to track the temperature before and during a run?

‘’’zsh
sudo powermetrics -s thermal --interval 2000
‘’’

Thermal level: Watch for Nominal, Fair, Serious, or Critical status to see if your MLX job is causing throttling

‘’’zsh
brew install macmon && macmon’’’
to run it along side your mlx run. blow all the dust out with compressed air very gently.

vsan

MLX Community org 2 days ago

You're also welcome to paste a pic of the results here so we can see the data for ourselves to understand.

vsan

MLX Community org 2 days ago

sudo powermetrics -s thermal -i 2000
This is the working command if the previous one doesnt work.

ginestopo

MLX Community org 2 days ago

Do you guys think this will work well in my macbook pro m4 pro 24GB? I'll be happy to post the results there. And is it possible to run it with ollama?