Gemma‑4‑E4B‑it is the second largest dense model in the new family of open LLMs from Google, offering solid performance with extremely economical resource consumption. The model uses the innovative Per‑Layer Embeddings (PLE) technique, which fundamentally changes the approach to building small language models. In standard transformers, each token receives a single embedding vector that passes through all network layers. PLE works differently: each of the 42 decoder layers gets its own small embedding per token. These embeddings are stored in large tables (the total model size reaches 8 billion parameters), but during inference only the effective part — 4.5 billion — is active.
This architecture allows the E4B model to achieve performance comparable to models two to three times larger. According to community feedback, E4B confidently surpasses Gemma‑3 27B in several tasks, even though its effective size is 12 times smaller. The model supports a context window of 128 thousand tokens and uses hybrid attention with a sliding window of 512 tokens. A key difference between E4B and the larger 31B model is built‑in audio support (an encoder of ~300M parameters), which makes the model universal — it can simultaneously process text, images, and sound.
Developers position E4B as a model for complex local tasks. It is ideally suited for use on high‑performance laptops, powerful mobile devices, and embedded systems. Thanks to the Apache 2.0 licence, the model can be freely fine‑tuned and integrated into commercial products that operate under tight memory constraints.
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
| Model Name | Context | Type | GPU | Status | Link |
|---|
There are no public endpoints for this model yet.
An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.
A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.
We recommend creating private endpoints when you need to:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 |
1 | $0.53 | 96.70 | 4.339 | Launch | |
131,072.0 |
1 | $0.83 | 143.43 | 5.136 | Launch | |
131,072.0 |
1 | $1.02 | 169.50 | 4.729 | Launch | |
131,072.0 tensor |
2 | $1.56 | 14.354 | Launch | ||
131,072.0 |
1 | $1.59 | 8.154 | Launch | ||
131,072.0 |
1 | $2.37 | 157.20 | 28.671 | Launch | |
131,072.0 |
1 | $3.83 | 171.74 | 23.092 | Launch | |
131,072.0 |
1 | $4.11 | 200.66 | 28.188 | Launch | |
131,072.0 tensor |
2 | $4.61 | 61.450 | Launch | ||
131,072.0 |
1 | $4.74 | 44.438 | Launch | ||
131,072.0 tensor |
2 | $9.40 | 92.688 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 |
1 | $0.53 | 42.76 | 1.627 | Launch | |
131,072.0 |
1 | $0.83 | 67.22 | 2.075 | Launch | |
131,072.0 |
1 | $1.02 | 134.00 | 2.109 | Launch | |
131,072.0 tensor |
2 | $1.56 | 11.173 | Launch | ||
131,072.0 |
1 | $1.59 | 5.369 | Launch | ||
131,072.0 tensor |
4 | $1.82 | 2.887 | Launch | ||
131,072.0 |
1 | $2.37 | 100.87 | 26.152 | Launch | |
131,072.0 |
1 | $3.83 | 117.24 | 21.205 | Launch | |
131,072.0 |
1 | $4.11 | 160.81 | 25.896 | Launch | |
131,072.0 tensor |
2 | $4.61 | 58.270 | Launch | ||
131,072.0 |
1 | $4.74 | 42.146 | Launch | ||
131,072.0 tensor |
2 | $9.40 | 90.071 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.