gemma-4-E2B-it

reasoning
multimodal

Gemma‑4‑E2B‑it is the most compact and energy‑efficient model in the lineup, designed to operate under extremely tight resource constraints. Like the E4B version, it uses the Per‑Layer Embeddings (PLE) technique, which delivers high performance with minimal memory consumption. The model has a total of 5.1 billion parameters, but only the effective part — 2.3 billion — is active during inference. It is built on 35 layers, supports a context window of 128 thousand tokens, and uses hybrid attention with a sliding window of 512 tokens.

E2B is fully multimodal and can process not only text and images but also audio (equipped with an audio encoder of ~300M parameters). This feature set, combined with extremely low memory requirements, makes the model unique in its class. Developers emphasise that E2B is specifically designed for efficient local use on laptops and mobile devices. According to community estimates, the model can run on devices with less than 1.5 GB of RAM, including smartphones.

Despite its modest size, E2B delivers impressive results. Numerous independent community evaluations show that this model surpasses Gemma‑3 27B on some tasks, even though its effective size is 12 times smaller. Developers particularly recommend E2B for routine agentic workflows, optical character recognition (OCR) tasks, and scenarios where low latency and on‑device inference are critical. At the same time, the Apache 2.0 licence opens up broad opportunities for integrating the model into a wide variety of commercial applications.

For the developers’ usage recommendations for the model, please refer to this link - https://ai.google.dev/gemma/docs/core/model_card_4?hl=en


Announce Date: 02.03.2026
Parameters: 6B
Context: 132K
Layers: 35, using full attention: 7
Attention Type: Sliding Window Attention
Developer: Google DeepMind
Transformers Version: 5.5.0.dev0
License: Apache 2.0

Public endpoint

Use our pre-built public endpoints for free to test inference and explore gemma-4-E2B-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-4-E2B-it

Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
131,072.0
1 $0.33 4.605 Launch
teslaa2-1.16.32.160
131,072.0
1 $0.38 4.605 Launch
teslaa10-1.16.32.160
131,072.0
1 $0.53 11.107 Launch
rtx2080ti-2.12.64.160
131,072.0
tensor
2 $0.69 7.224 Launch
rtx3090-1.16.24.160
131,072.0
1 $0.83 11.107 Launch
rtx3080-2.16.32.160
131,072.0
tensor
2 $0.97 5.599 Launch
rtx4090-1.16.32.160
131,072.0
1 $1.02 11.107 Launch
teslav100-1.12.64.160
131,072.0
1 $1.20 17.609 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 28.355 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 17.609 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 56.619 Launch
h100-1.16.64.160
131,072.0
1 $3.83 56.619 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 67.997 Launch
h200-1.16.128.160
131,072.0
1 $4.74 106.195 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
131,072.0
1 $0.33 3.044 Launch
teslaa2-1.16.32.160
131,072.0
1 $0.38 3.044 Launch
teslaa10-1.16.32.160
131,072.0
1 $0.53 9.546 Launch
rtx2080ti-2.12.64.160
131,072.0
tensor
2 $0.69 5.663 Launch
rtx3090-1.16.24.160
131,072.0
1 $0.83 9.546 Launch
rtx3080-2.16.32.160
131,072.0
tensor
2 $0.97 4.037 Launch
rtx4090-1.16.32.160
131,072.0
1 $1.02 9.546 Launch
teslav100-1.12.64.160
131,072.0
1 $1.20 16.047 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 26.793 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 16.047 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 55.058 Launch
h100-1.16.64.160
131,072.0
1 $3.83 55.058 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 66.436 Launch
h200-1.16.128.160
131,072.0
1 $4.74 104.634 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
131,072.0
1 $0.33 2.128 Launch
teslaa2-1.16.32.160
131,072.0
1 $0.38 2.128 Launch
teslaa10-1.16.32.160
131,072.0
1 $0.53 8.630 Launch
rtx2080ti-2.12.64.160
131,072.0
tensor
2 $0.69 4.747 Launch
rtx3090-1.16.24.160
131,072.0
1 $0.83 8.630 Launch
rtx3080-2.16.32.160
131,072.0
tensor
2 $0.97 3.122 Launch
rtx4090-1.16.32.160
131,072.0
1 $1.02 8.630 Launch
teslav100-1.12.64.160
131,072.0
1 $1.20 15.132 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 25.878 Launch
rtx5090-1.16.64.160
131,072.0
1 $1.59 15.132 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 54.142 Launch
h100-1.16.64.160
131,072.0
1 $3.83 54.142 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 65.521 Launch
h200-1.16.128.160
131,072.0
1 $4.74 103.718 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.