Gemma 3 27B
LegacyAffordableRun locallyGoogle's open multimodal model with 128K context and 140+ language support.
Supports vision-language input with improved math, reasoning, and multilingual capabilities. Superseded by Gemma 4 series.
▼
Gemma 3 27B by Google has a Capability Index of 64.6, making it comparable to the field average. It ranks #61 out of 92 models on the idapt capability leaderboard. Gemma 3 27B is somewhat expensive at $0.10/M tokens input and $0.30/M tokens output. The model supports vision/image input, a 110K context window.
Benchmarks
Category Rankings
Specifications
Performance
Providers
Run locally
Run Gemma 3 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 gemma3:27b-it-q4_K_M
Misc
Compare with
Frequently Asked Questions about Gemma 3 27B▼
When was Gemma 3 27B released?
▼
Gemma 3 27B was released on March 12, 2025.
Who created Gemma 3 27B?
▼
Gemma 3 27B was created by Google.
How capable is Gemma 3 27B?
▼
Gemma 3 27B has a Capability Index of 64.6/100, making it comparable to the field average. It ranks #61 out of 92 models.
How much does Gemma 3 27B cost?
▼
Gemma 3 27B costs $0.10/M input tokens and $0.30/M output tokens.
What is Gemma 3 27B API pricing?
▼
The Gemma 3 27B API is priced at $0.10 per million input tokens and $0.30 per million output tokens. You can access Gemma 3 27B through idapt.app alongside 200+ other AI models in one workspace.
Is Gemma 3 27B a reasoning model?
▼
No, Gemma 3 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 3 27B support image or vision input?
▼
Yes, Gemma 3 27B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Gemma 3 27B support audio?
▼
No, Gemma 3 27B does not support audio input.
What is the context window of Gemma 3 27B?
▼
Gemma 3 27B has a context window of 110K tokens, meaning it can process approximately 82,500 words of context at once.
Is Gemma 3 27B open source?
▼
Gemma 3 27B is a proprietary model developed by Google. The model weights and training data are not publicly available.
What is Gemma 3 27B good at?
▼
Based on benchmark data, Gemma 3 27B excels at: visual analysis and image understanding. It is Google's capable model suitable for a wide range of tasks.
Where can I use Gemma 3 27B?
▼
You can chat with Gemma 3 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 3 27B through Google's own API or platform.