← Latest products

Needle

We Distilled Gemini Tool Calling into a 26M Model. 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. We open-sourced Needle, a 26M parameter function-calling (tool use) model.

Open source

14,428 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Cactus Needle 3

    cactuscompute.com

    8-29MB automation models can match DeepSeek V4 Flash

    Hacker News537 pts

  2. Clai

    github.com

    Vendor agnostic Claude Code/Gemini CLI written in Go

    Hacker News11 pts

  3. Bonsai 1.7B ternary model at 442T/s on M4 Max

    agents2agents.ai

    A drop-in optimized inference build of Bonsai 1.7B for Apple Silicon. ~42% faster decode (tg128) and ~9% faster prefill (pp512) on M-series GPUs. All Metal kernels written and tuned by ata, our autonomous engineering agent.

    Hacker News13 pts

  4. OpenGraviton

    opengraviton.github.io

    Run 500B+ parameter models on a consumer Mac Mini

    Hacker News13 pts

  5. 1-Bit Bonsai

    prismml.com

    the First Commercially Viable 1-Bit LLMs

    Hacker News430 pts