WebLLM
Run large language models in your browser with WebGPU
No screenshot yet
About WebLLM
WebLLM runs open language models entirely in the browser using WebGPU, with no server. Try its chat demo, or build it into your own web apps through an OpenAI-style API.
Found in
Alternatives to WebLLM
183kGitHub starsOllama
Run open large language models on your own machine
156kGitHub starsOpen WebUI
Self-hosted chat interface for local and remote AI models
138kGitHub starsComfyUI
Node-based workflows for local image and video generation
50kGitHub starsUpscayl
AI image upscaler that runs locally on your GPU
