MicroLLM Lab – Try 7 tiny LLM's in the browser
Run Q4 small language models entirely in the browser with WebGPU. Chat, benchmark, and compare PetitGPT, SmolLM2, and friends on-device.
Summary
Experiment with seven compact language models directly in your browser, using WebGPU for enhanced performance. Chat and benchmark models like PetitGPT and SmolLM2 to see how they stack up against each other.
Comments (113 of ) ⌛