WebLLM is a high-performance in-browser LLM inference engine powered by WebGPU, enabling developers to run large language models directly in the browser without remote servers. Supports popular models like Llama, Mistral, and Phi. 18K+ GitHub stars.
WebLLM is a high-performance in-browser LLM inference engine powered by WebGPU, enabling developers to run large language models directly in the browser without remote servers. Supports popular models like Llama, Mistral, and Phi. 18K+ GitHub stars.