#128 · Primary category： Inference & Local Deploy
wllama
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
Project last updated：08/27/26
GitHub Stars
1.2K
Forks
119
Contributors
9
License
MIT
Why we included this project
wllama brings llama.cpp to the browser by compiling it to WebAssembly, so a GGUF model runs entirely on the user's machine with no backend to stand up. It ships as an npm package with a typed OpenAI-compatible API, which means teams already calling chat completions or embeddings can switch to in-browser inference without rewriting much of their integration. WebGPU support offloads layers to the GPU when available, and vision inputs and tool calling are covered as well. Inference runs inside a worker so the page stays responsive, and larger models can be split into chunks that download in parallel, working around the 2GB file-size limit. The one gotcha is that multithreading requires setting the Cross-Origin-Embedder-Policy and Cross-Origin-Opener-Policy headers.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.