needle cactus-compute
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
- Language
- Python
- Stars
- 4,988
- Forks
- 334
Tags
- 库/SDK
- 工具调用
- 嵌入式
- 本地部署
- 推理优化
- 深度学习
- Python
README
 # Needle 2 Needle 2 is an open 45M-parameter model for tool calling, device use and structured extraction. The whole model is a single 14MB binary that runs a full session in about 28MB of RAM. It is built on our Simple Attention Network findings, compressed to CQ2-bit …