9B instruction-tuned Gemma 2
According to the model card, this is the instruction-tuned 9B Gemma 2 text-to-text decoder-only variant with open weights.
Open Source Model Profile · google
gemma-2-9b-it
gemma-2-9b-it is a 9.24B-parameter Gemma 2 instruction-tuned model from Google for English text generation with an 8-trillion-token base.
- Publisher
- Task
- text-generation
- Model type
- gemma2
- License
- gemma
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
gemma-2-9b-it is published by Google as a Gemma 2 instruction-tuned text-generation model. The captured configuration identifies Gemma2ForCausalLM and Safetensors metadata reports 9,241,705,984 parameters. According to the model card, it is a text-to-text decoder-only English model built with Gemini technology, and card data records gemma.
Recorded capabilities
QA, summarization, reasoning scope
The publisher describes the models as suited to question answering, summarization, and reasoning, including deployment on a laptop, desktop, or cloud infrastructure.
Large-scale documented training
According to the model card, the 9B model trained on 8 trillion tokens using TPUv5p hardware with JAX and ML Pathways.
Reported safety evaluation
The model card says ethics and safety evaluations fell within internal thresholds and publishes RealToxicity, BBQ, Winogender, TruthfulQA, and Toxigen figures.
Use cases in the source record
- English question answering, summarization, and reasoning work using text-string inputs and the publisher's chat-template format.
- GPU inference with Transformers pipelines or torch-compile acceleration, following the documented single- and multi-GPU examples.
Limitations and unknowns
- No context-window value was extracted from this record.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- Safety and benchmark figures are publisher-reported model-card values and were not independently verified by Ethen.
Source and provenance
Source: google/gemma-2-9b-it
Captured: Unknown. Processed: 2026-09-07T19:34:45.614512+00:00.
Gemma 2 model card Model Page : Gemma Resources and Technical Documentation : Responsible Generative AI Toolkit Gemma on Kaggle Gemma on Vertex Model Garden Terms of Use : Terms Authors : Google 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. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a v…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015F017F022F024F029F034F040F041F042