← Latest products

Maple-Preview

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

Visit deepgrove.aiexternal site

Reactions (1)

Similar products

by description similarity

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

    github.com

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

    Hacker News24 pts

  2. Finetune Llama-3 2x faster in a Colab notebook

    colab.research.google.com

    Hacker News45 pts

  3. A iOS Native Bluesky App

    github.com

    I made a Bluesky app that's 100% Swift based.

    Hacker News20 pts

  4. OpenGraviton

    opengraviton.github.io

    Run 500B+ parameter models on a consumer Mac Mini

    Hacker News13 pts

  5. Faster Internet for the Middle Class

    github.com

    Smaller files for the Middle Class

    Hacker News14 pts