gemma-3-12b-it

multimodal

Gemma 3 12B is a well-balanced mid-sized multimodal language model developed by Google DeepMind, designed to tackle narrow, specialized professional tasks. With 12 billion parameters, the model combines high performance with computational efficiency and supports a wide range of capabilities—from text analysis to image processing. Gemma 3 12B converts visual data into tokens, enabling deep understanding of images. The "Pan&Scan" technology allows adaptive processing of images with any aspect ratio, preserving detail when scaling up to a resolution of 896×896.

Another key feature is the expanded context window of up to 128K tokens. This enables the model to process lengthy legal documents and scientific articles in a single request without losing context. Multilingual support covers more than 140 languages, including Russian, while the enhanced tokenizer from Gemini 2.0 ensures high-quality translation, text generation, and cross-lingual analysis. Additionally, developer-supported quantization makes it possible to run the model even on consumer-grade GPUs with minimal loss in quality.

As a result, Gemma 3 12B is a versatile tool for data analysis, document processing, and information extraction from visual sources—with the ability to run locally and scalable integration into modern AI infrastructures.


Announce Date: 12.03.2025
Parameters: 12B
Context: 132K
Layers: 48, using full attention: 8
Attention Type: Sliding Window Attention
Developer: Google DeepMind
Transformers Version: 4.50.0.dev0
License: gemma

Public endpoint

Use our pre-built public endpoints for free to test inference and explore gemma-3-12b-it capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended server configurations for hosting gemma-3-12b-it

Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 2.272 Launch
teslaa2-3.32.128.160
131,072.0
pipeline
3 $1.06 8.87 1.575 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 3.185 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 92.00 2.950 Launch
rtx3090-2.16.64.160.nvlink
131,072.0
tensor
2 $1.56 2.950 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 1.147 Launch
rtx3080-4.16.64.160
131,072.0
tensor
4 $1.82 1.265 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 124.25 2.468 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 106.97 4.361 Launch
h100-1.16.64.160
131,072.0
1 $3.83 94.06 4.142 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 5.091 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 9.476 Launch
h200-1.16.128.160
131,072.0
1 $4.74 8.319 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 17.845 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 54.50 2.504 Launch
teslaa2-3.32.128.160
131,072.0
pipeline
3 $1.06 1.761 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 3.418 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 80.29 2.708 Launch
rtx3090-2.16.64.160.nvlink
131,072.0
tensor
2 $1.56 2.708 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 1.378 Launch
rtx3080-4.16.64.160
131,072.0
tensor
4 $1.82 1.498 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 86.72 2.700 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 83.57 4.300 Launch
h100-1.16.64.160
131,072.0
1 $3.83 96.29 4.295 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 5.256 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 9.642 Launch
h200-1.16.128.160
131,072.0
1 $4.74 8.484 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 18.011 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 1.437 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 16.66 2.337 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 52.27 1.641 Launch
rtx3090-2.16.64.160.nvlink
131,072.0
tensor
2 $1.56 1.641 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 1.633 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 3.539 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 3.140 Launch
h100-1.16.64.160
131,072.0
1 $3.83 61.70 3.534 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 4.495 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 8.876 Launch
h200-1.16.128.160
131,072.0
1 $4.74 7.723 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 17.245 Launch

Related models

Need help?

Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.

We use cookies and web analytics services to ensure the proper functioning of the website, analyze web-site traffic, and improve the quality of our services.
By continuing to use the website, you consent to the Privacy Policy and consent to the processing of cookie files and technical data.