Gemma 2 27B
LegacyStandardRun locallySecond-generation open model from Google DeepMind.
Built from same research as Gemini. Well-suited for text generation tasks and fine-tuning. Superseded by Gemma 3 series.
▼
Gemma 2 27B by Google has a Capability Index of 56.8, making it below the field average in capability. It ranks #72 out of 92 models on the idapt capability leaderboard. Gemma 2 27B is somewhat expensive at $0.65/M tokens input and $0.65/M tokens output. The model supports a 8K context window.
Benchmarks
Category Rankings
Specifications
Performance
Providers
Run locally
Run Gemma 2 27B on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull gemma2:27b-instruct-q4_K_M
Misc
Compare with
Frequently Asked Questions about Gemma 2 27B▼
When was Gemma 2 27B released?
▼
Gemma 2 27B was released on July 13, 2024.
Who created Gemma 2 27B?
▼
Gemma 2 27B was created by Google.
How capable is Gemma 2 27B?
▼
Gemma 2 27B has a Capability Index of 56.8/100, making it below the field average in capability. It ranks #72 out of 92 models.
How much does Gemma 2 27B cost?
▼
Gemma 2 27B costs $0.65/M input tokens and $0.65/M output tokens.
What is Gemma 2 27B API pricing?
▼
The Gemma 2 27B API is priced at $0.65 per million input tokens and $0.65 per million output tokens. You can access Gemma 2 27B through idapt.app alongside 200+ other AI models in one workspace.
Is Gemma 2 27B a reasoning model?
▼
No, Gemma 2 27B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Gemma 2 27B support image or vision input?
▼
No, Gemma 2 27B does not currently support image or vision input. It is a text-only model.
Does Gemma 2 27B support audio?
▼
No, Gemma 2 27B does not support audio input.
What is the context window of Gemma 2 27B?
▼
Gemma 2 27B has a context window of 8K tokens, meaning it can process approximately 6,144 words of context at once.
Is Gemma 2 27B open source?
▼
Gemma 2 27B is a proprietary model developed by Google. The model weights and training data are not publicly available.
Where can I use Gemma 2 27B?
▼
You can chat with Gemma 2 27B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Gemma 2 27B through Google's own API or platform.