A dense Gemma 4 for assistants, analytics and document and image work. Solid reasoning and tool calling at moderate memory requirements.
| MMLU Pro | 77.2 | |
|---|---|---|
| GPQA Diamond | 78.8 | |
| LiveCodeBench v6 | 72 |
Which GPU does Gemma 4 12B need?
The entry configuration is 1x RTX3090, which delivers around 36 tokens per second. For more parallel requests and headroom on speed, go with 1x H200.
How much does Gemma 4 12B cost?
An hour of Gemma 4 12B runs from $0.59 to $8.20 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.
How do I call Gemma 4 12B from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass gemma4:12b as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. Gemma 4 12B runs on a dedicated GPU server inside a private environment: requests and responses never reach the model vendor and are not used for training.
What context window and license does Gemma 4 12B have?
Gemma 4 12B holds 32K tokens of context per request and ships under the Apache 2.0 license, so you can use it commercially on your own hosting terms.