# WebLLM

Framework · https://godooo.ai/en/framework/webllm

> WebLLM is an open-source AI framework, launched in 2023, made for developers.

A JavaScript engine that runs LLMs entirely in the browser with WebGPU.

Main jobs: LLM API, Run models locally. It is open source and free to use. You can use it in the browser and offline on your own machine.

## At a glance

- **Type:** [Framework](https://godooo.ai/en/browse#framework)
- **Launched:** 2023
- **Galaxy:** [Models & APIs](https://godooo.ai/en/galaxy/builders)
- **Open source:** Yes · Apache-2.0
- **Source code:** [github.com/mlc-ai/web-llm](https://github.com/mlc-ai/web-llm)
- **GitHub stars:** 19,183
- **How you run it:** Web · Runs offline
- **Made for:** Developers
- **Protocols:** [OpenAI-compatible API](https://godooo.ai/en/protocol/openai-compatible-api)
- **Website:** [webllm.mlc.ai](https://webllm.mlc.ai)
- **Also known as:** Web LLM

## What it can do

- **[LLM API](https://godooo.ai/en/capability/llm-api)** — main job, _proposed by a machine, awaiting calibration_. “WebLLM is fully compatible with OpenAI API.” (read on [github.com](https://github.com/mlc-ai/web-llm), 2026-09-24)
- **[Run models locally](https://godooo.ai/en/capability/local-inference)** — main job, _proposed by a machine, awaiting calibration_. “WebLLM is a high-performance in-browser LLM inference engine that brings language model inference directly onto web browsers with hardware acceleration.” (read on [github.com](https://github.com/mlc-ai/web-llm), 2026-09-24)
- **[Chat and Q&A](https://godooo.ai/en/capability/chat)** — supported, _proposed by a machine, awaiting calibration_. “Supports streaming chat completions, allowing real-time output generation which enhances interactive applications like chatbots and virtual assistants.” (read on [webllm.mlc.ai](https://webllm.mlc.ai/), 2026-09-24)

## Alternatives

- **[Llama](https://godooo.ai/en/model/llama)** (Open source, free): Also does: Chat and Q&A, LLM API, Run models locally
- **[Qwen](https://godooo.ai/en/model/qwen)** (Open source, free): Also does: Chat and Q&A, LLM API, Run models locally; no code needed
- **[GLM](https://godooo.ai/en/model/glm)** (Open source, free): Also does: Chat and Q&A, LLM API, Run models locally
- **[Jan](https://godooo.ai/en/product/jan)** (Open source, free): Also does: Chat and Q&A, Run models locally, LLM API; no code needed
- **[LocalAI](https://godooo.ai/en/framework/localai)** (Open source, free): Also does: LLM API, Run models locally
- **[Mixtral](https://godooo.ai/en/model/mixtral)** (Open source, free): Also does: Chat and Q&A, LLM API, Run models locally
- **[Phi](https://godooo.ai/en/model/phi)** (Open source, free): Also does: Chat and Q&A, Run models locally, LLM API
- **[TextGen](https://godooo.ai/en/product/textgen)** (Open source, free): Also does: Chat and Q&A, Run models locally, LLM API; no code needed
- **[gpt-oss](https://godooo.ai/en/model/gpt-oss)** (Open source, free): Also does: Run models locally, Chat and Q&A, LLM API
- **[Kimi K2](https://godooo.ai/en/model/kimi-k2)** (Open source, free): Also does: LLM API, Chat and Q&A, Run models locally
- **[LLM](https://godooo.ai/en/cli/llm)** (Open source, free): Also does: LLM API, Chat and Q&A, Run models locally
- **[LM Studio](https://godooo.ai/en/product/lm-studio)** (Free): Also does: Run models locally, Chat and Q&A, LLM API; no code needed

## Connections

- **Built with:** [MLC LLM](https://godooo.ai/en/framework/mlc-llm)

## Questions

### What is WebLLM?

WebLLM is an open-source AI framework, launched in 2023, made for developers. A JavaScript engine that runs LLMs entirely in the browser with WebGPU.

### Is WebLLM free?

Yes. WebLLM is open source (Apache-2.0) and free to use.

### Is WebLLM open source?

Yes, under the Apache-2.0 license. The source code is at https://github.com/mlc-ai/web-llm.

### Can WebLLM run locally?

Yes. WebLLM can run offline on your own machine.

### What can WebLLM do?

Main jobs: LLM API, Run models locally. It can also do: Chat and Q&A.

### What are open-source alternatives to WebLLM?

Open-source ones: Llama, Qwen, GLM, Jan, LocalAI, Mixtral, Phi and TextGen. Others: LM Studio.

## Sources

- [github.com](https://github.com/mlc-ai/web-llm) — checked 2026-09-24
- [webllm.mlc.ai](https://webllm.mlc.ai/) — checked 2026-09-24

---

Last updated 2026-09-24 · sources checked 2026-09-24 · Markdown version of https://godooo.ai/en/framework/webllm. Every page on this site has one: add .md to its address.