Gemma 3n E4B
by Google · gemma-3 family
4B
parameters
text-generation reasoning multilingual vision
Gemma 3n E4B is Google's efficient 4B-parameter multimodal model from the Gemma 3n family, designed for on-device and edge deployment. It supports both text and vision inputs, making it versatile for a wide range of tasks while maintaining a small footprint. Built with efficiency as a primary goal, the E4B variant delivers strong multilingual and reasoning capabilities in a package small enough to run on devices with limited memory, including smartphones and embedded systems.
Quick Start with Ollama
ollama run e4b-q4_K_M | Creator | |
| Parameters | 4B |
| Architecture | transformer-decoder |
| Context | 32K tokens |
| Released | Sep 10, 2025 |
| License | Gemma Terms of Use |
| Ollama | gemma3n:e4b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 2.5 GB | 4.5 GB | | e4b-q4_K_M |
| Q8_0 | 4.2 GB | 6.5 GB | | e4b-q8_0 |
| F16 | 8 GB | 11 GB | | e4b-fp16 |
Compatible Hardware
Q4_K_M requires 4.5 GB VRAM