← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

Edge0

github.com

Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

Open source

Visit github.comexternal siteGitHub9,125 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE

    Metal-first MoE inference for Apple Silicon with bounded SSD expert streaming and local OpenAI Chat, Responses, and Anthropic Messages endpoints.

    github.comDesktopOpen source2 reactionslatest reaction

    Hacker News
    24 pts
    GitHub
    67 stars

  2. Capy-flash

    a 125B MoE model on two 16 GB consumer GPUs

    github.comOpen source2 reactionslatest reaction

    Hacker News
    8 pts
    GitHub
    140 stars

  3. Maple-Preview

    Ternary 20B MoE running at 120 tok/s on a iPhone

    deepgrove.ailatest reaction

    Hacker News
    173 pts
    GitHub
    No reaction

  4. RunNburn

    Run a 295B Moe from a 98GB GGUF on a 64GB RAM Desktop

    github.comOpen source2 reactionslatest reaction

    Hacker News
    11 pts
    GitHub
    28 stars

  5. xtuner

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    5,222 stars