google/gemma-3-270m
Text Generation • 0.3B • Updated • 101k • 1.02k
Lists some sub-1b parameter text-to-text small language models, perfect for edge use, smartphones, or generally weak hardware for below 2GB of RAM.
Note the best sub-half-billion parameter model out there
Note legit makes smollm v1 and v2 seem obsolete
Note most neglected lfm2 model btw