runlocal.devCheck My GPU →

Gemma 4 E2B

MoEApache 2.0

Google's ultra-compact multimodal MoE. Only 2.3B active params with full text/image/audio support. Lowest VRAM entry point in the Gemma 4 family.

Provider

Google

Parameters

2.3B active / 5B total

Context

131.072K

Released

2026-04-08

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
Q8_05 GB6 GB15 GPUs
Q4_K_M2.8 GB3.5 GB15 GPUs
Q4_02.6 GB3.2 GB15 GPUs

Install with Ollama

Run in terminal:

ollama pull gemma4:e2b

Minimum 3.2GB VRAM required. Install Ollama from ollama.com

Benchmark Scores

mmlu72%
humaneval52%

Scores are approximate and may vary by quantization level.

Compatible GPUs (15)

HuggingFace

google/gemma-4-e2b-it

View on HF →