Instructions to use spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spanthee/qwen3-macos-clawdia-toolcalling-mlx-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("spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 "spanthee/qwen3-macos-clawdia-toolcalling-mlx-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": "spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 "spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit

Run Hermes

hermes

OpenClaw new

How to use spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 "spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 "spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 spanthee/qwen3-macos-clawdia-toolcalling-mlx-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 "spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3 8B macOS Clawdia Tool-Calling MLX 4-bit

Fused MLX 4-bit model for local-first tool calling in Clawdia-style chat. It was trained from Qwen3 8B with LoRA/QLoRA data focused on:

macOS app, file, reminder, note, timer, mail, and AppleScript workflows
Cua Driver / computer-use style tools
Clawdia internal tools and schema-conditioned tool selection
Browser navigation plans for everyday sites
Adaptive tool use when tool names and parameter names change

This is the direct MLX inference artifact. You do not need to load a separate adapter.

Local MLX usage

python -m mlx_lm chat \
  --model spanthee/qwen3-macos-clawdia-toolcalling-mlx-4bit \
  --temp 0.1 \
  --top-p 0.9 \
  --max-tokens 1200

For tool-calling use, include the available tool list and schemas in the prompt. The model was trained to treat the tool list in the current prompt as authoritative rather than relying on memorized tool names.

Eval snapshot

Current local evidence reports 184/184 included tool-calling eval passes with strict JSON output on the included rows. Some reported passes use harness-level postprocessing for runtime-safe normalization, so raw-output behavior should be validated in the target Clawdia runtime before treating the model as complete.

Known weak area: multimodal receipt-image extraction is not covered by this text-only Qwen artifact. Receipt-image support is being evaluated separately with Gemma VLM.