Back to Calculator
Gemma 3n E4B
HotGoogle's Gemma 3 nano E4B with on-demand weight loading, multimodal with text/image/audio input, 4B effective params
Model Specifications
ArchitectureVISION
Parameters8B
Familygemma
VRAM (Q4)4.0GB
On-demand architecture: weights loaded per-token. ~8GB total, ~4B effective active
Share this Model
Send this model's specs directly to your community.
Similar Models
Related Guides
How much VRAM do you really need?
A complete breakdown of quantization levels and VRAM overhead for running local models.
Best GPUs for Machine Learning in 2026
Comparing NVIDIA and AMD options for the best speed-to-dollar ratio.
GGUF vs EXL2 vs AWQ
Understanding local AI formats and which one to pick for your specific hardware.