gemma-3-1b-it

Gemma 3 1B — a compact language model developed by Google DeepMind, achieving an impressive balance between size and capabilities. With just 1 billion parameters and a context window of 32,000 tokens, the model is highly efficient and capable of running on devices with limited resources. Thanks to its architecture, Gemma 3 1B optimizes memory usage, making it an ideal choice for embedded systems and mobile applications.

It's important to note that the 1B version is a text-only model and does not support image processing, unlike the larger variants in the Gemma 3 series (4B, 12B, and 27B), which offer multimodal capabilities.

Additionally, the model has limited language support and is primarily optimized for tasks in English.

Gemma 3 1B is available with open weights, making it easy to fine-tune and adapt to specific use cases. It comes in multiple quantization levels, ranging from 32-bit down to 4-bit, providing added flexibility when deploying on different hardware platforms.


Announce Date: 12.03.2025
Parameters: 1B
Context: 33K
Layers: 26, using full attention: 4
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-3-1b-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-3-1b-it

Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
32,768.0
1 $0.33 29.792 Launch
rtx2080ti-1.10.16.500
32,768.0
1 $0.38 17.828 Launch
teslaa2-1.16.32.160
32,768.0
1 $0.38 52.190 29.911 Launch
teslaa10-1.16.32.160
32,768.0
1 $0.53 70.130 53.540 Launch
rtx3080-1.16.32.160
32,768.0
1 $0.57 14.987 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 56.710 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 56.591 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 55.054 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 80.010 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 99.990 223.275 Launch
h100-1.16.64.160
32,768.0
1 $3.83 103.880 223.066 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 205.740 264.670 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 224.789 Launch
h200-1.16.128.160
32,768.0
1 $4.74 404.376 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 405.890 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
32,768.0
1 $0.33 29.792 Launch
rtx2080ti-1.10.16.500
32,768.0
1 $0.38 17.828 Launch
teslaa2-1.16.32.160
32,768.0
1 $0.38 29.912 Launch
teslaa10-1.16.32.160
32,768.0
1 $0.53 53.540 Launch
rtx3080-1.16.32.160
32,768.0
1 $0.57 14.987 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 56.710 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 56.591 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 55.054 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 80.010 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 223.275 Launch
h100-1.16.64.160
32,768.0
1 $3.83 223.066 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 264.670 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 224.789 Launch
h200-1.16.128.160
32,768.0
1 $4.74 404.376 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 405.890 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
32,768.0
1 $0.33 26.765 Launch
rtx2080ti-1.10.16.500
32,768.0
1 $0.38 14.801 Launch
teslaa2-1.16.32.160
32,768.0
1 $0.38 51.260 26.884 Launch
teslaa10-1.16.32.160
32,768.0
1 $0.53 62.650 50.513 Launch
rtx3080-1.16.32.160
32,768.0
1 $0.57 11.960 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 53.683 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 53.564 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 53.540 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 76.983 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 110.850 220.248 Launch
h100-1.16.64.160
32,768.0
1 $3.83 116.270 220.039 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 260.990 261.643 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 223.276 Launch
h200-1.16.128.160
32,768.0
1 $4.74 401.349 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 404.377 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.