Skip to main content
Google DeepMindReleased June 27, 2024

Gemma 2 27B

Open Source#18 Arena Rank27B parameters

Gemma 2 27B holds a solid spot in the Arena rankings at #18. Context window: 0.008K tokens.

Context

8K

Input

Free (open)

Key Specifications

🏆

Arena Rank

#18

📐

Context Window

8K

📥

Input Price

per 1M tokens

Free (open)

📤

Output Price

per 1M tokens

Free (open)

🧠

Parameters

27B

🔓

Open Source

Yes

Best For

Researchfine-tuningon-premise deployment

About Gemma 2 27B

Gemma 2 27B, developed by Google DeepMind, is the largest model in the Gemma 2 open-source family with 27 billion parameters and an 8K token context window. The model delivers performance competitive with much larger open-source alternatives while requiring less compute for inference. Its architecture incorporates knowledge distillation techniques from larger Gemini models, achieving strong results on reasoning, coding, and multilingual benchmarks. Gemma 2 27B supports fine-tuning and can run on a single high-end consumer GPU, making it practical for on-premise enterprise deployments with data privacy requirements. As a fully open-source model with permissive licensing, it enables commercial deployment without API costs. Gemma 2 27B ranks #18 on the Chatbot Arena leaderboard, placing it among the strongest open-weight models in its parameter class.

Pricing per 1M tokens

Input Tokens

Free (open)

Output Tokens

Free (open)

Frequently Asked Questions

What is Gemma 2 27B?
Gemma 2 27B, developed by Google DeepMind, is the largest model in the Gemma 2 open-source family with 27 billion parameters and an 8K token context window. The model delivers performance competitive with much larger open-source alternatives while requiring less compute for inference. Its architecture incorporates knowledge distillation techniques from larger Gemini models, achieving strong results on reasoning, coding, and multilingual benchmarks. Gemma 2 27B supports fine-tuning and can run on a single high-end consumer GPU, making it practical for on-premise enterprise deployments with data privacy requirements. As a fully open-source model with permissive licensing, it enables commercial deployment without API costs. Gemma 2 27B ranks #18 on the Chatbot Arena leaderboard, placing it among the strongest open-weight models in its parameter class.
How much does Gemma 2 27B cost?
Google DeepMind charges Free (open) per 1M input tokens for Gemma 2 27B, with output at Free (open). Competitive with other models in its tier.
What is Gemma 2 27B's context window?
Gemma 2 27B supports up to 8K tokens per request. A larger context window allows the model to reason over longer inputs, which matters for document analysis, code review, and multi-turn conversations.
Is Gemma 2 27B open source?
Yes — Google DeepMind released Gemma 2 27B as open source. That means you're free to deploy it however you want: cloud, on-prem, edge. No API lock-in.
What is Gemma 2 27B best for?
Google DeepMind positions Gemma 2 27B for: Research, fine-tuning, on-premise deployment. Real-world performance will depend on your specific prompts and data, but these are the intended strengths.