Instructions to use mlx-community/gpt-oss-20b-OptiQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-4bit

Run Hermes

hermes

OpenClaw new

How to use mlx-community/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/gpt-oss-20b-OptiQ-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/gpt-oss-20b-OptiQ-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

很棒的模型，比其他人的oss-20B都好

by ZhudaAndZhuer - opened 3 days ago

Discussion

ZhudaAndZhuer

3 days ago

在不做任何外部工程的情況下，第一款能通過我全部測試，並且得到達到分數93/100的模型．
設備：Mac Air M4 24GB
效率：31 t/s Average

附上測試圖，模型配上Harness工程化的Server + OpneCode Agent，很完美．
測試在codex或claude會負擔太重，最佳建議是自行建置輕量的Harness Agent or Loop Agent.

codelion

MLX Community org 3 days ago

謝謝你這麼詳細的測試與回饋！看到它在 M4 Air 24GB 上一次通過你全部測試、拿到 93/100，還能跑到 31 t/s，真的很開心。

OptiQ 的混合精度量化就是為了這種記憶體吃緊的 Mac 設計的:把最敏感的層留在 8-bit、其餘壓到 4-bit，所以在相同大小下會比一般的 uniform 4-bit 更耐用。

也很認同你的建議,這類模型搭配輕量的 harness / loop agent 效果最好,你的 OpenCode 組合看起來很棒。謝謝分享,歡迎隨時回報使用心得！

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