← Latest products

RunAnywhere (YC W26)

Faster AI Inference on Apple Silicon. Get up and running with GLM-5.3-flash, DeepSeek, Gemma and other open source frontier models. We built a fast inference engine for Apple Silicon.

Open source

1,570 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. We made our own inference engine for Apple Silicon

    github.com

    A high-performance inference engine for AI models

    Hacker News186 pts

  2. Magnitude (YC S25)

    github.com

    Self-optimizing inference engine for agents

    Hacker News194 pts

  3. Inferencer

    inferencer.com

    Run and deeply control local AI models (macOS release)

    Hacker News15 pts

  4. Gemma 3 inference in pure C++ with Metal acceleration

    github.com

    Pure C++23 LLM inference for Apple Silicon chips

    Hacker News6 pts

  5. Cactus (YC S25)

    github.com

    AI inference on smartphones

    Hacker News231 pts