A very small chat

A tiny language model running in your browser. It is experimental, so expect short answers and occasional nonsense.

Stentor-30M-Instruct

30M parameters · 512-token context · runs on this device

The first load downloads the model. Your prompts stay in this browser.

When the model is ready, send it a short question.

Model by StentorLabs, quantized to GGUF Q4_K_M by mradermacher · Apache-2.0