login sign up

MicroLLM lab — tiny LLMs, Q4, in your browser

stateofutopia.com · first added by @kmurph
saved by
0 people
discussions · 1
MicroLLM Lab – Try 7 tiny LLM's in the browser 284 pts · 113 comments · Sep 2026 284 pts · 113 comments · Sep 2026
0 people saved or upvoted this
from the discussion · 5
tiny tiny stories tiny.tobelabs.com tiny.tobelabs.com
0 people saved or upvoted this
Gemma 4 E2B · WebGPU willaaam.github.io willaaam.github.io
0 people saved or upvoted this
TinyStories: How Small Can Language Models Be and Still Speak Coherent English? arxiv.org arxiv.org
0 people saved or upvoted this
WebGPU | Can I use... Support tables for HTML5, CSS3, etc caniuse.com caniuse.com
0 people saved or upvoted this
GitHub - willaaam/gemma-4-E2B-webgpu-vision: (Probably) The fastest browser based Gemma 4 E2B implementation with vision support. Comes with a workstation to interact with the model. Use AI fully air-gapped and offline, you just need a browser. github.com github.com
0 people saved or upvoted this