Blazing-fast WebGPU runtime - Open Source

Engineered in Rust and C++, Sipp keeps model weights and tokens on-device, minimizing copies across the WASM boundary for real-time games, local agents, and vision/chat apps on WebGPU or desktop. When work moves beyond the device, the same API extends to self-hosted gateways or trusted providers.

Open sourceWebGPU fast pathSelf-host gateway

SippPink Lemonade Ed.

Nutrition Facts

Serving size: 1 Sipp Client

Amount per pour

  • Dependencies0
  • Model formatGGUF
  • EngineRust + C++ + GGML
  • BackendBrowser-nativeWebGPU

% Dev Value

  • Open source100%
  • Type-safe100%
  • Endpoint mixer1 API

$ npm install @sipphq/sipp

Ingredients

WebGPU, WASM, Rust, C++, GGUF, TypeScript, OPFS-backed cache, gateways, providers. Contains no black-box runtime, no framework lock-in, no added sugar.

Taste test

Easy Setup.
One Simple API.

Initialize local WebGPU inference, stream real tokens, and keep GGUF weights in browser storage for repeat runs. Offload to a self-hosted gateway or trusted provider when need, same API.

  • Local Model Setup
    Load GGUF weights into WebGPU from a single API, with no server path required.
  • Explicit Endpoint Mixing
    Register local, gateway, or provider targets and mix between them.
  • Native Hot Path
    Let Rust and C++ handle scheduling, memory, token throughput, and gateway builds.

Benchmark · WebGPU showdown

Same model.
Faster in the browser.

Sipp's WebGPU backend cuts TTFT and runs decode up to 3x faster against other browser runtimes while keeping the same GGUF weights local. No native install. Pick a model and inspect the multipliers.

Sipp vs

Transformers.js

8.4×

faster

TTFT8.4× faster

Sipp

1×

Decode3.8× tok/s

Sipp

1×

E2E latency3.5× faster

Sipp

1×

Sipp vs

WebLLM

5.4×

faster

TTFT5.4× faster

Sipp

1×

Decode3.5× tok/s

Sipp

1×

E2E latency3.3× faster

Sipp

1×

Measured on Qwen 2.5 0.5B · Q4_K_M. LILO · 1024 in / 512 out · NVIDIA 3080 · Chrome (N=3, 9 runs, 1 warmup). Multipliers show how many times faster Sipp runs vs each browser runtime.

Live demo · Fresh squeeze

Pick a model.
Sip the tokens.

A bare-bones chat running 100% in your browser. Pick a model, start the tap, and then chat. No account, no server.

Try the full demo

Built with Sipp · 100% in-browser

Pour it into
anything.

Real apps running real models with Sipp. No servers, no install, no waiting. Every one runs the model right in your browser.

Mobile support is currently being worked on. Try demos on desktop.

GameDesktop

🪄Desktop only

A wizard duel where every spell is generated on the fly by a local LLM. No two casts the same.

Desktop only

GameLocal

🪄Live demo

A wizard duel where every spell is generated on the fly by a local LLM. No two casts the same.

Play in browser ›

AgentsDesktop

🍌Desktop only

A swarm of little agents reason in-browser, each running a local model to pick its next move, all fighting for one banana.

Desktop only

AgentsLocal

🍌Live demo

A swarm of little agents reason in-browser, each running a local model to pick its next move, all fighting for one banana.

Play in browser ›

VisionDesktop

🎨Desktop only

Draw something and a local vision model snapshots the canvas, reads it, and gives you live feedback.

Desktop only

VisionLocal

🎨Live demo

Draw something and a local vision model snapshots the canvas, reads it, and gives you live feedback.

Play in browser ›

ChatDesktop

💬Desktop only

Chat with a VRM character whose emotes, actions, and replies are all chosen live by a local model.

Desktop only

ChatLocal

💬Live demo

Chat with a VRM character whose emotes, actions, and replies are all chosen live by a local model.

Play in browser ›

One client - every target

Start in the browser.
Mix where it runs.

The same endpoint API follows you to native runtimes, trusted provider calls, and a self-hosted gateway when you want one boundary for local and remote work.

FeaturedWebGPU · zero install

Browser

Run GGUF weights in the browser on WebGPU. Zero install when the work fits on-device, with the same client model available when it does not.

$ npm install @sipphq/sippRead the browser docs ›

Fresh batch ready

Pour your first inference.

Install Sipp, run a GGUF model in your browser on WebGPU, then use the same endpoint model across Node, Rust, Python, and the self-hosted gateway.