Cactus: Ollama for Smartphones
Published:Jul 10, 2025 19:20
•1 min read
•Hacker News
Analysis
Cactus is a cross-platform framework for deploying LLMs, VLMs, and other AI models locally on smartphones. It aims to provide a privacy-focused, low-latency alternative to cloud-based AI services, supporting a wide range of models and quantization levels. The project leverages Flutter, React-Native, and Kotlin Multi-platform for broad compatibility and includes features like tool-calls and fallback to cloud models for enhanced functionality. The open-source nature encourages community contributions and improvements.
Key Takeaways
- •Cross-platform framework for local AI model deployment on smartphones.
- •Supports a wide range of GGUF models and quantization levels.
- •Offers tool-calls for enhanced functionality and cloud fallback for complex tasks.
- •Open-source and built with Flutter, React-Native & Kotlin Multi-platform.
Reference
“Cactus enables deploying on phones. Deploying directly on phones facilitates building AI apps and agents capable of phone use without breaking privacy, supports real-time inference with no latency...”