Google Gemma 4 12B
p/gemma-4-12bRun multimodal AI locally with an encoder-free architecture
•0 reviews•52 followers
Start new thread
trending
Rohan Chaubey•

3h ago

Google Gemma 4 12B - Run multimodal AI locally with an encoder-free architecture

Gemma 4 12B processes text, vision, and audio natively without separate encoders, running on 16GB VRAM. For developers building local agentic applications who need multimodal capability without cloud dependency.