Trending/LLM & models

LLM & models

cactus-compute/needle

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots,…

★ 14.3KWeek rank 178 · star gain starts at the next snapshot

View on GitHub

From the README

A foundation model for mobiles, wearables, robots, smart home, automotive and microcontrollers. The whole model is a single 8-29 MB binary built on our Simple Attention Network, and we trade general chat capacity to beat models 10x its size on mobile tool calls and match 2-3x bigger models on extraction.

Setup prompt

Paste this into Cursor or Claude Code. It only includes install lines found in the README, and it asks the agent to review the code first.

Set up the GitHub repository cactus-compute/needle (Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.).
Repository: https://github.com/cactus-compute/needle

Official install commands found in the README:
pip install cactus-needle

Clone the repository and follow those steps. Do not invent package names or extra install commands.
Review the code before running anything.

Buzz by window

Same mentions, three half-lives. This is not a star history. Star gain appears after a second daily snapshot.

  • Today0.00
  • Week0.00
  • Month0.00

Spotted on

Related

Report a problem or request removal