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
teslat4-3.32.64.160
131,072.0
pipeline
3 $0.88 1.904 Launch
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 2.321 Launch
teslat4-4.16.64.160
131,072.0
tensor
4 $0.96 2.837 Launch
teslaa2-3.32.128.160
131,072.0
pipeline
3 $1.06 1.914 Launch
rtx2080ti-4.16.32.160
131,072.0
tensor
4 $1.12 1.476 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 2.321 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 2.851 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 90.410 2.502 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 1.465 Launch
rtx3080-4.16.64.160
131,072.0
tensor
4 $1.82 1.153 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 2.495 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 5.541 Launch
h100-1.16.64.160
131,072.0
1 $3.83 5.535 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 6.718 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 11.979 Launch
h200-1.16.128.160
131,072.0
1 $4.74 10.693 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 22.283 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-3.32.64.160
131,072.0
pipeline
3 $0.88 1.628 Launch
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 2.045 Launch
teslat4-4.16.64.160
131,072.0
tensor
4 $0.96 2.561 Launch
teslaa2-3.32.128.160
131,072.0
pipeline
3 $1.06 1.638 Launch
rtx2080ti-4.16.32.160
131,072.0
tensor
4 $1.12 1.200 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 2.045 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 2.575 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 2.226 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 1.189 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 2.219 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 5.265 Launch
h100-1.16.64.160
131,072.0
1 $3.83 5.259 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 6.442 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 11.703 Launch
h200-1.16.128.160
131,072.0
1 $4.74 10.417 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 22.007 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 1.119 Launch
teslat4-4.16.64.160
131,072.0
tensor
4 $0.96 1.635 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 1.119 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 1.649 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 1.299 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 1.293 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 4.339 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 2.625 Launch
h100-1.16.64.160
131,072.0
1 $3.83 4.333 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 5.516 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 10.777 Launch
h200-1.16.128.160
131,072.0
1 $4.74 9.491 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 21.081 Launch

Related models

Need help?

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