Instructions to use badtheorylabs/Macaw-4bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use badtheorylabs/Macaw-4bit-MLX 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("badtheorylabs/Macaw-4bit-MLX") 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
- Pi
How to use badtheorylabs/Macaw-4bit-MLX with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "badtheorylabs/Macaw-4bit-MLX"
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": "badtheorylabs/Macaw-4bit-MLX" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use badtheorylabs/Macaw-4bit-MLX with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "badtheorylabs/Macaw-4bit-MLX"
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 "badtheorylabs/Macaw-4bit-MLX" \ --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 badtheorylabs/Macaw-4bit-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "badtheorylabs/Macaw-4bit-MLX"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "badtheorylabs/Macaw-4bit-MLX" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "badtheorylabs/Macaw-4bit-MLX", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use badtheorylabs/Macaw-4bit-MLX 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 "badtheorylabs/Macaw-4bit-MLX"
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 badtheorylabs/Macaw-4bit-MLX
Run Hermes
hermes
Reproducible packaging/model issue
Macaw-4bit-MLX generates the correct first Pythonic tool call through MLX-LM 0.31.3, but after a successful role:tool result it repeats the identical call indefinitely. This persists when the result is formatted as read_file: created-on-host, when the tools array is removed, and when tool_choice is set to none. Adding "tool_parser_type":"pythonic" was necessary for structured OpenAI output.
HTTP_STATUS=$(
curl -sS
-o /tmp/macaw-roundtrip-no-tools-response.json
-w '%{http_code}'
http://127.0.0.1:8138/v1/chat/completions
-H 'Content-Type: application/json'
--data-binary @/tmp/macaw-roundtrip-no-tools.json
)
echo "HTTP status: $HTTP_STATUS"
jq . /tmp/macaw-roundtrip-no-tools-response.json
HTTP status: 200
{
"id": "chatcmpl-dc6d4d94-c6c1-4e85-8683-6290d797a21b",
"system_fingerprint": "0.31.3-0.32.0-macOS-27.0-arm64-arm-64bit-Mach-O-applegpu_g16g",
"object": "chat.completion",
"model": "default_model",
"created": 1786038850,
"choices": [
{
"index": 0,
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"tool_calls": [
{
"function": {
"name": "read_file",
"arguments": "{"path": "/workspace/host-test.txt"}"
},
"type": "function",
"id": "f2ce30fa-9e1b-4d6d-b81d-14f11c601610"
}
]
}
}
],
"usage": {
"prompt_tokens": 71,
"completion_tokens": 17,
"total_tokens": 88,
"prompt_tokens_details": {
"cached_tokens": 0
}
}
}
HTTP_STATUS=$(
curl -sS
-o /tmp/macaw-roundtrip-tool-none-response.json
-w '%{http_code}'
http://127.0.0.1:8138/v1/chat/completions
-H 'Content-Type: application/json'
--data-binary @/tmp/macaw-roundtrip-tool-none.json
)
echo "HTTP status: $HTTP_STATUS"
jq . /tmp/macaw-roundtrip-tool-none-response.json
HTTP status: 200
{
"id": "chatcmpl-45ac9601-5714-4114-afbc-b4524945020f",
"system_fingerprint": "0.31.3-0.32.0-macOS-27.0-arm64-arm-64bit-Mach-O-applegpu_g16g",
"object": "chat.completion",
"model": "default_model",
"created": 1786038868,
"choices": [
{
"index": 0,
"finish_reason": "tool_calls",
"message": {
"role": "assistant",
"tool_calls": [
{
"function": {
"name": "read_file",
"arguments": "{"path": "/workspace/host-test.txt"}"
},
"type": "function",
"id": "4cb4f39a-5fa8-4720-a6fe-96633abe379e"
}
]
}
}
],
"usage": {
"prompt_tokens": 136,
"completion_tokens": 17,
"total_tokens": 153,
"prompt_tokens_details": {
"cached_tokens": 0
}
}
}
this has been fixed. thank you for flagging it