Retour à Gemma 3
Google's 27B Gemma 3 multimodal instruct model — strongest of the Gemma 3 family with vision understanding and 128K context.
131K tokensGratuit / Poids ouvertsimageTransformerGemma Terms
Benchmarks
BFCL v4
gemma-3-27b-it
29.5%gemma-3-4b-it
19.6%gemma-3-1b-it
7.2%Gemma-3-27b-it Prompt — rank #69