llm
A small language model running entirely in your browser.
No server, no API key. Your prompt never leaves your machine.
SmolLM2-1.7B, multi-turn chat.
SmolLM2-1.7B-Instruct Q4_0, multi-turn chat via WebGPU with lean.
Qwen2.5-0.5B-Instruct Q4_0 (~429MB) via lean compiled to WebAssembly.