Description
State-of-the-art image + text input models from Google, built from the same research and tech used to create the Gemini models
Capabilities
Vision Input
Trained for tool use
Minimum system memory
11GB
Tags
12B
gemma3
Last updated
Updated on July 3byREADME
gemma 3 12b it by google
Supports a context length of 128k tokens, with a max output of 8192.
Multimodal supporting images normalized to 896 x 896 resolution.
Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning.
Requires latest (currently beta) llama.cpp runtime.
Sources
The underlying model files this model uses