GoogleGemma 4
Gemma 4 E4B
A larger effective-size Gemma 4 checkpoint.
What the release provides
It has 4.5B effective parameters, 8B with embeddings, a 128K context and text, image and audio input. Apache 2.0 applies.Google Gemma 4 model card
How to use it well
Practical guidance. Compare the actual deployment against E2B on tasks that require more reasoning or visual detail. Keep the precision and context settings fixed during comparison. The useful result is the quality and responsiveness on your device, not the model label alone.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | google/gemma-4-E4B-it |