Lucy
A 1.7B model built for web search through tool calling, small enough to bring search-powered answers to phones and low-power devices.
Overview
- Parameters
- 1.7B
- Base model
- Qwen3-1.7B
- Context
- 128k
- Built for
- Web search through tool calling
- License
- Apache 2.0
78.3%
SimpleQA accuracy (YaRN 130k)
Lucy is a 1.7B parameter model built on Qwen3-1.7B, optimized for web search through tool calling. The model has been trained to work effectively with search APIs like Serper, enabling web search capabilities in resource-constrained environments.
Try it in JanPerformance
SimpleQA Benchmark
Lucy achieves competitive performance on SimpleQA despite its small size:
| Benchmark | Jan-nano-128k-MCP (YaRN 130k) | Jan-nano-MCP | Jan-nano-MCP (YaRN 130k) | Lucy (YaRN 130k) | DeepSeek-V3-MCP | ChatGPT-4.5 | Baseline-MCP | Gemini-2.5-Pro | Claude-3.7-Sonnet | o3 | Grok-3 | o1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SimpleQA (Question answering accuracy) | 83.2% | 80.7% | 79.7% | 78.3% | 78.2% | 62.5% | 59.2% | 52.9% | 50% | 49.4% | 44.6% | 42.6% |
The benchmark shows Lucy (1.7B) compared against models ranging from 4B to 600B+ parameters. While larger models generally perform better, Lucy demonstrates that effective web search integration can partially compensate for smaller model size.
Requirements
- Memory:
- Minimum: 4GB RAM (with Q4 quantization)
- Recommended: 8GB RAM (with Q8 quantization)
- Search API: Serper API key required for web search functionality
- Hardware: Runs on CPU or GPU
Using Lucy
Quick Start
- Download Jan Desktop
- Download Lucy from the Hub
- Configure Serper MCP with your API key
- Start using web search through natural language
Demo

Deployment Options
Using vLLM:
vllm serve Menlo/Lucy-128k \ --host 0.0.0.0 \ --port 1234 \ --enable-auto-tool-choice \ --tool-call-parser hermes \ --rope-scaling '{"rope_type":"yarn","factor":3.2,"original_max_position_embeddings":40960}' \ --max-model-len 131072
Using llama.cpp:
llama-server model.gguf \ --host 0.0.0.0 \ --port 1234 \ --rope-scaling yarn \ --rope-scale 3.2 \ --yarn-orig-ctx 40960
Recommended Parameters
Temperature: 0.7Top-p: 0.9Top-k: 20Min-p: 0.0
What Lucy Does Well
- Web Search Integration: Optimized to call search tools and process results
- Small Footprint: 1.7B parameters means lower memory requirements
- Tool Calling: Reliable function calling for search APIs
Limitations
- Requires Internet: Web search functionality needs active connection
- API Costs: Serper API has usage limits and costs
- Context Processing: While supporting 128k context, performance may vary with very long inputs
- General Knowledge: Limited by 1.7B parameter size for tasks beyond search
Downloads
- Jan: Download Jan
- Lucy-128k: Hugging Face (opens in a new tab) GGUF (opens in a new tab)
Citation
Dao, A., Vu, D. B., Nguyen, A., & Buppodom, N. (2025). Lucy: edgerunning agentic web search on mobile with machine generated task vectors. arXiv:2508.00360.
Talk to us
- Discussions: Hugging Face community (opens in a new tab)
- Chat: Discord (opens in a new tab)
- Issues: GitHub (opens in a new tab)



