Chat Gemma 3 270M

Running locally with jax-js + WebGPU

Options

Backend

WebGPU uses fp16 weights. Wasm casts weights to fp32 on load.

Max new tokens Top-k Temperature: 0.80 Top-p: 0.95

KV cache is allocated dynamically for the current chat.

Talk to an LLM

The first message downloads and caches a 536 MB fp16 checkpoint. Everything runs locally in your browser.