mlc-ai/web-llm

High-performance In-browser LLM Inference Engine

276 best points · 105 comments · 4 Hacker News posts · 19,359 GitHub stars · View on GitHub

Hacker News discussions

• Web LLM – WebGPU Powered Inference of Large Language Models (276 points, 80 comments, by summarity, 2023-04-15)
• WebLLM: high-performance in-browser LLM inference engine (145 points, 25 comments, by saikatsg, 2026-09-02)
• Web LLM (6 points, 0 comments, by crowwork, 2023-04-15)
• WebLLM is a high-performance in-browser LLM inference engine (1 points, 0 comments, by doener, 2026-05-02)