Gemma 4 31B
Google DeepMindGemma 4 12B eliminates these encoders entirely, projecting raw image patches and audio waveforms directly into the LLM's embedding space through lightweight linear layers.
4 more from this model
Gemma 4 12B eliminates these encoders entirely, projecting raw image patches and audio waveforms directly into the LLM's embedding space through lightweight linear layers.
we trained Gemma 4 12B with an encoder-free architecture to integrate audio and vision input directly.
This unified approach means all modalities flow straight into a single decoder-only transformer
We introduce a unified encoder-free architecture for the 12B model, which projects raw 40ms audio chunks and image patches into the LLM embedding space, alleviating the need for separate encoders and reducing memory fragmentation.