Multimodal input and context
According to the model card, Gemma 3 handles text and image input with 128K context for the 12B size and 8192 output tokens.
Open Source Model Profile · unsloth
gemma-3-12b-it
gemma-3-12b-it is a 12.19B-parameter Gemma 3 multimodal model from unsloth for text and image input with text output.
- Publisher
- unsloth
- Task
- image-text-to-text
- Model type
- gemma3
- License
- gemma
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
gemma-3-12b-it is published by unsloth as an image-text-to-text model. Safetensors metadata reports 12,187,325,040 parameters, with Gemma3ForConditionalGeneration and model type gemma3. According to the model card, it follows the Gemma 3 multimodal design for text and image input.
Recorded capabilities
Transformers and pipeline usage
The model card documents pipeline-API initialization and single- or multi-GPU use with AutoProcessor and Gemma3ForConditionalGeneration.
Documented training setup
The model card says the 12B model was trained on 12 trillion tokens using TPU hardware with JAX and ML Pathways.
Use cases in the source record
- Image understanding plus text generation, including question answering, summarization, and reasoning over text and 896 x 896 images.
- Transformers pipeline and accelerated GPU inference using the documented processor and conditional-generation class.
Limitations and unknowns
- No evaluation results were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Limitations, bias, factual-accuracy, and safety statements are publisher disclosures and were not independently verified by Ethen.
Source and provenance
Source: unsloth/gemma-3-12b-it
Captured: Unknown. Processed: 2026-09-07T19:35:32.137618+00:00.
Gemma 3 model card Model Page : Gemma Resources and Technical Documentation : Gemma 3 Technical Report Responsible Generative AI Toolkit Gemma on Kaggle Gemma on Vertex Model Garden Terms of Use : Terms Authors : Google DeepMind Model Information Summary description and brief definition of inputs and outputs. Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned vari…
F001F002F003F004F005F006F007F009F010F011F013F014F015F016F018F023F027F031F033F035F036