Instructions to use mlx-community/Qwen3-235B-A22B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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/Qwen3-235B-A22B-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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"

MLX LM

How to use mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/Qwen3-235B-A22B-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/Qwen3-235B-A22B-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/Qwen3-235B-A22B-4bit

Run Hermes

hermes

Token generation speed is very slow

by huynguyendbs - opened May 22, 2025

Discussion

huynguyendbs

May 22, 2025

@Awni

I saw your post on X mentioning an inference speed of around ~28 toks/s. However, when I tried running this model using mlx_lm on my Mac M2 Ultra, the inference speed was only about ~1 toks/s.

I installed mlx_lm using the command pip install mlx-lm and tested it with the command:
mlx_lm.generate --model mlx-community/Qwen3-235B-A22B-4bit --max-tokens 4096 --prompt "/no-think How are you?"

Could you share how you installed and ran mlx_lm to achieve that speed?

awni

MLX Community org May 22, 2025

It needs a 192GB machine to work well. How much RAM do you have?

huynguyendbs

May 22, 2025

•

edited May 22, 2025

@Awni
My device is M2 Ultra 192GB RAM
It seems like my GPU isn't operating at full capacity. I'm not sure if I might have missed some setup or configuration.

awni

MLX Community org May 22, 2025

What OS are you on? For wired memory it's important to be on OS 15. That can make a big difference for very large models.

huynguyendbs

May 22, 2025

@Awni
It seems like I'm still on macOS 14.5. I will update to macOS 15 and test it again.
Thank you very much.

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