Views
No views yet
1# Download and run instantly
2ollama create qwen3:toolcall -f ModelFile
3ollama run qwen3:toolcall1# Ask: "Get weather data for New York and format it as JSON"
2# Model automatically calls weather API with proper parameters1# Ask: "Analyze this CSV file and create a visualization"
2# Model selects appropriate tools: pandas, matplotlib, etc.1# Ask: "Fetch stock data, calculate moving averages, and email me the results"
2# Model orchestrates multiple function calls seamlessly1# Load with Ollama
2import requests
3
4response = requests.post('http://localhost:11434/api/generate', json={
5 'model': 'qwen3:toolcall',
6 'prompt': 'Get the current weather in San Francisco and convert to Celsius',
7 'stream': False
8})
9
10print(response.json()['response'])1# The model understands complex tool orchestration
2prompt = """
3I need to:
41. Fetch data from the GitHub API
52. Process the JSON response
63. Create a visualization
74. Save it as a PNG file
8
9What tools should I use and how?
10"""| Feature | This Model | Cloud APIs | Other Local Models |
|---|---|---|---|
| Cost | Free after download | $0.01-0.10 per call | Often larger/heavier |
| Privacy | 100% local | Data sent to servers | Varies |
| Speed | Instant | Network dependent | Often slower |
| Reliability | Always available | Service dependent | Depends on setup |
| Customization | Full control | Limited | Varies |
1@model{Qwen3-4B-toolcalling-gguf-codex,
2 title={Qwen3-4B-toolcalling-gguf-codex: Local Function Calling},
3 author={Manojb},
4 year={2025},
5 url={https://huggingface.co/Manojb/Qwen3-4B-toolcalling-gguf-codex}
6}