Launch HN: RunAnywhere (YC W26) — Fast AI Inference on Apple Silicon

1 min read

YC-backed startup ships an inference engine using MetalRT that claims to outperform existing solutions for LLMs, speech-to-text, and TTS on Apple Silicon. Aims to make Mac hardware a first-class AI development platform.

// share this

// get daily digest

Top 10 dev stories every morning at 8am UTC. AI-curated. Retro terminal HTML email.