New release: Gemma 3 family of models
New release: Gemma 3 family of models
huggingface.co Gemma 3 Release - a google Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
GGUF quants are already up and llama.cpp was updated today to support it.
2
comments
Im especially interested in its advanced OCR capabilities. Will be testing this one out on lm studio
I tested these out and found they are really bad at longer context... at least in settings that can sanely fit on most GPUs.
Seems the Gemma family is mostly for short-context work, still.