

WebLLM
#8 in Lokale LLM-Runtimesmlc-ai · siet Dezember 2024 · 5× · tolest 30. Juni 2026
21
Momentum
WebLLM is an open-source JavaScript library from MLC-AI that runs large language models directly in web browsers with WebGPU acceleration. It compiles quantized models through Apache TVM to WebAssembly, enabling local inference without server requests. The API is compatible with OpenAI standards.
Momentum-Verloop
04.04.03.07.
Features
| Provider | MLC AI (Machine Learning Compilation) |
| Model Type | LLM inference engine with multi-model support (Llama 3, Phi 3, Gemma, Mistral, Qwen) |
| Price Tier | Free (Open-Source) |
| Availability | Open-source (free); npm package @mlc-ai/web-llm |