Gemma 3 12B
LegacyAffordableRun locallyMid-size open multimodal model balancing capability and efficiency.
Vision-language input, 128K context window, multilingual support. Superseded by Gemma 4 series.
▼
Gemma 3 12B is somewhat expensive at $0.05/M tokens input and $0.15/M tokens output. The model supports vision/image input, a 131K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Run locally
Run Gemma 3 12B 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 gemma3:12b-it-q4_K_M
Misc
Compare with
GPT 5.6 Solvs Gemma 3 12BGPT 5.6 Lunavs Gemma 3 12B
Claude Fable 5vs Gemma 3 12BClaude Opus 4.8vs Gemma 3 12BClaude Sonnet 5vs Gemma 3 12BClaude Haiku 4.5vs Gemma 3 12B
Gemini 3.6 Flashvs Gemma 3 12BGemini 3.5 Flashvs Gemma 3 12BGemini 3.5 Flash-Litevs Gemma 3 12BGemma 4 31Bvs Gemma 3 12B
Grok 4.5vs Gemma 3 12BGrok Build 0.1vs Gemma 3 12BGrok 4.1 Fastvs Gemma 3 12B
Muse Spark 1.1vs Gemma 3 12B
DeepSeek V4 Provs Gemma 3 12BDeepSeek V4 Flashvs Gemma 3 12B
MiniMax M3vs Gemma 3 12B
GLM 5.2vs Gemma 3 12B
Qwen3.7 Maxvs Gemma 3 12BQwen3.7 Plusvs Gemma 3 12BQwen3 Coder Nextvs Gemma 3 12B
Nemotron 3 Ultravs Gemma 3 12B
Mistral Small 4vs Gemma 3 12BFrequently Asked Questions about Gemma 3 12B▼
When was Gemma 3 12B released?
▼
Gemma 3 12B was released on March 13, 2025.
Who created Gemma 3 12B?
▼
Gemma 3 12B was created by Google.
How much does Gemma 3 12B cost?
▼
Gemma 3 12B costs $0.05/M input tokens and $0.15/M output tokens.
What is Gemma 3 12B API pricing?
▼
The Gemma 3 12B API is priced at $0.05 per million input tokens and $0.15 per million output tokens. You can access Gemma 3 12B through idapt.app alongside 200+ other AI models in one workspace.
Is Gemma 3 12B a reasoning model?
▼
No, Gemma 3 12B 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 12B support image or vision input?
▼
Yes, Gemma 3 12B 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 12B support audio?
▼
No, Gemma 3 12B does not support audio input.
What is the context window of Gemma 3 12B?
▼
Gemma 3 12B has a context window of 131K tokens, meaning it can process approximately 98,304 words of context at once.
Is Gemma 3 12B open source?
▼
Gemma 3 12B is a proprietary model developed by Google. The model weights and training data are not publicly available.
What is Gemma 3 12B good at?
▼
Based on benchmark data, Gemma 3 12B 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 12B?
▼
You can chat with Gemma 3 12B 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 12B through Google's own API or platform.