Gemma 4 E4B
by Google · gemma-4 family
4B
parameters
text-generation code-generation reasoning multilingual vision
Gemma 4 E4B is Google's efficient 4.5B-effective-parameter multimodal model, ideal for laptops and consumer devices. It delivers a significant quality leap over its predecessor Gemma 3n E4B while maintaining a similar footprint. Supports text and vision inputs with 128K context. At Q4 it needs about 6 GB of VRAM, fitting comfortably on entry-level GPUs and 8 GB Macs.
Quick Start with Ollama
ollama run e4b-it-q4_K_M | Creator | |
| Parameters | 4B |
| Architecture | transformer-decoder |
| Context | 128K tokens |
| Released | Apr 2, 2026 |
| License | Apache 2.0 |
| Ollama | gemma4:e4b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 9.6 GB | 6 GB | | e4b-it-q4_K_M |
| Q8_0 | 12 GB | 10 GB | | e4b-it-q8_0 |
Compatible Hardware
Q4_K_M requires 6 GB VRAM