Gemma 2 9B Instruct

Gemma 2 9B Instruct, developed by Google, is a state-of-the-art large language model based on the advanced Gemini framework. It is a decoder-only transformer model with 9 billion parameters, offering a balance between size and performance. The model is trained on an expansive dataset comprising 8 trillion tokens, including web documents, code, and mathematical text, a notable 30% increase from its predecessor, Gemma 1.1. This allows it to adeptly handle diverse tasks such as question answering, creative writing, coding, and mathematical problem-solving. However, it shares common limitations of large language models, such as potential biases and the risk of generating inaccuracies or outdated information. Notably, Gemma 2 9B Instruct incorporates Grouped-Query Attention (GQA) and uses the GeGLU activation function, and is specifically fine-tuned to follow instructions and participate effectively in multi-turn dialogues.

Gemma 2 9B Instruct is an open-weight model in the Gemma 2 family. The structured metadata tracks a 8k-token context window and structured outputs. This page tracks provider routes through Fireworks AI, NVIDIA NIM, OpenRouter, and 2 more, with the cheapest tracked route listed at $0.1 input and $0.1 output per 1M tokens. Headline tracked benchmarks include Instruction-Following Evaluation 65.5.