🦞🌯 Lobster Roll

Stories by sanchitmonga22

Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon (github.com)
Hi HN, we&#x27;re Sanchit and Shubham (YC W26). We built a fast inference engine for Apple Silicon. LLMs, speech-to-text, text-to-speech – MetalRT beats llama.cpp, Apple&#x27;s MLX, Ollama, and sherpa-onnx on every modality we tested. Custom Metal shaders, no framework overhead.<p>Also, we&#x27;ve o...
Show HN: On-device browser agent (Qwen) running locally in Chrome (github.com)
Demo of LOCAL Browser agent (powered by Web GPU Liquid LFM &amp; Alibaba Qwen models) opening the All in Podcast on Youtube running as a chrome extension.<p>Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;RunanywhereAI&#x2F;on-device-browser-agent" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F...
Fastest LLM decode engine on Apple Silicon. 658 tok/s on M4-max,beats mlx by 19% (runanywhere.ai)
Runanywhere – Make every CPU and GPU count (github.com)