Gemma 4 E2B
by Google · gemma-4 family
2B
parameters
text-generation reasoning multilingual vision
Gemma 4 E2B is Google's smallest Gemma 4 model with 2.3B effective parameters, designed for edge and mobile deployment. Despite its compact size, it supports vision input and 140+ languages with a 128K context window. At Q4 it needs just 4 GB of VRAM, making it one of the most capable models you can run on virtually any hardware — including phones and Raspberry Pi devices.
Quick Start with Ollama
ollama run e2b-it-q4_K_M | Creator | |
| Parameters | 2B |
| Architecture | transformer-decoder |
| Context | 128K tokens |
| Released | Apr 2, 2026 |
| License | Apache 2.0 |
| Ollama | gemma4:e2b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M rec | 7.2 GB | 4 GB | | e2b-it-q4_K_M |
| Q8_0 | 8.1 GB | 6 GB | | e2b-it-q8_0 |
Compatible Hardware
Q4_K_M requires 4 GB VRAM