← 최신 프로덕트

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.

오픈소스

14,442 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Cactus Needle 3

    cactuscompute.com

    8-29MB automation models can match DeepSeek V4 Flash

    Hacker News537점

  2. We beat Gemini Embedding 2 by training only 16M params (open weights)

    huggingface.co

    Feature Extraction model with 16.4M parameters. Download, explore files and run it on Hugging Face.

    Hacker News7점

  3. Local Coding Agent with LLMs to Delegate Tool Calls to Small AI Models

    github.com

    Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.

    Hacker News9점

  4. OpenGraviton

    opengraviton.github.io

    Run 500B+ parameter models on a consumer Mac Mini

    Hacker News13점

  5. Clai

    github.com

    Vendor agnostic Claude Code/Gemini CLI written in Go

    Hacker News11점