L

Lucy 128k

Developed by Menlo
Lucy is a 1.7-billion parameter model focused on intelligent web search and lightweight browsing. It is built on Qwen3-1.7B and optimized to run efficiently on mobile devices.
Downloads 109
Release Time : 7/18/2025

Model Overview

Lucy is a compact yet powerful 1.7-billion parameter model focused on intelligent web search and lightweight browsing. It is built on Qwen3-1.7B. While inheriting the powerful research capabilities of large models, it is optimized to run efficiently on mobile devices, even with only a CPU configuration.

Model Features

Powerful intelligent search capabilities
Supported by tools that support MCP (such as Serper integrated with Google Search).
Basic web browsing functionality
Can be implemented through Crawl4AI (MCP server to be released), Serper, etc.
Optimized for mobile devices
The model is lightweight and can run at a considerable speed on CPUs or mobile devices.
Focused inference capabilities
Optimizes the thinking process of search tasks through machine-generated task vectors.

Model Capabilities

Intelligent web search
Lightweight browsing
Text generation

Use Cases

Information retrieval
Intelligent web search
Use Lucy for efficient web search and information retrieval.
The accuracy on SimpleQA is higher than that of DeepSeek-v3.
Mobile device applications
Intelligent search on mobile devices
Deploy Lucy on mobile devices for intelligent search and browsing.
Runs at a considerable speed on CPUs or mobile devices.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase