# Deploy Google models on dedicated GPUs

19 Google models ready to deploy on GPU capacity reserved for you, from 268M to 31B parameters, covering chat & reasoning, embeddings, translation and safety & moderation. Private OpenAI-compatible endpoint, European GPUs, billed per GPU-hour.

| Model | Type | Params | Context | License | Page |
| --- | --- | --- | --- | --- | --- |
| gemma-4-31B-it | Chat & reasoning | 31B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-31B-it.md |
| gemma-4-E4B-it | Chat & reasoning | 8.0B | 128K | Apache 2.0 | https://sference.com/models/google/gemma-4-E4B-it.md |
| gemma-4-26B-A4B-it | Chat & reasoning | 26B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-26B-A4B-it.md |
| embeddinggemma-2 | Embeddings | 744M | 256K | Apache 2.0 | https://sference.com/models/google/embeddinggemma-2.md |
| embeddinggemma-300m | Embeddings | 303M | — | Gemma Terms of Use | https://sference.com/models/google/embeddinggemma-300m.md |
| gemma-4-12B-it | Chat & reasoning | 12B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-12B-it.md |
| gemma-3-1b-it | Chat & reasoning | 1000M | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3-1b-it.md |
| gemma-4-E2B-it | Chat & reasoning | 5.1B | 128K | Apache 2.0 | https://sference.com/models/google/gemma-4-E2B-it.md |
| gemma-3-4b-it | Chat & reasoning | 4.3B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-4b-it.md |
| medgemma-4b-it | Chat & reasoning | 4.3B | — | Custom license | https://sference.com/models/google/medgemma-4b-it.md |
| gemma-3-27b-it | Chat & reasoning | 27B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-27b-it.md |
| gemma-3-270m-it | Chat & reasoning | 268M | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3-270m-it.md |
| gemma-3-12b-it | Chat & reasoning | 12B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-12b-it.md |
| medgemma-27b-it | Chat & reasoning | 27B | — | Custom license | https://sference.com/models/google/medgemma-27b-it.md |
| gemma-3n-E4B-it | Chat & reasoning | 7.8B | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3n-E4B-it.md |
| gemma-3n-E2B-it | Chat & reasoning | 5.4B | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3n-E2B-it.md |
| translategemma-12b-it | Translation | 12B | — | Gemma Terms of Use | https://sference.com/models/google/translategemma-12b-it.md |
| shieldgemma-2-4b-it | Safety & moderation | 4.3B | — | Gemma Terms of Use | https://sference.com/models/google/shieldgemma-2-4b-it.md |
| translategemma-27b-it | Translation | 27B | — | Gemma Terms of Use | https://sference.com/models/google/translategemma-27b-it.md |

## FAQ

### Which Google models can I deploy on sference?

19 today, most requested first: gemma-4-31B-it, gemma-4-E4B-it, gemma-4-26B-A4B-it, embeddinggemma-2, embeddinggemma-300m, gemma-4-12B-it, gemma-3-1b-it and gemma-4-E2B-it, and 11 more. Any other Google checkpoint or a fine-tune of one can be requested with the form on this page.

### How many GPUs do Google models need?

It depends on the model: the lineup runs from 268M to 31B parameters. Each model page lists the checkpoint size and the minimum footprint on 80 GB and 141 GB GPUs. You don't pick hardware on sference: you choose a performance tier and we size the deployment.

### Can I use Google models commercially?

17 of the 19 listed models are under licenses that allow commercial use (Apache 2.0, Gemma Terms of Use and Custom license across the lineup). Each model page summarizes its license and links the full text.

### How is a dedicated deployment priced?

Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.

Request a deployment: https://sference.com/models/google#request. All makers: https://sference.com/dedicated.md