Gemma 4 E4B
Google · released Apr 2, 2026
| size | 8 B / 4.5 B effective |
| context window | 128,000 tokens |
| longest response | not stated by the maker |
| knowledge cutoff | January 2025 |
| open weights | yes, license: Apache 2.0 |
| how it ran | run locally on my computer |
| input and output | text, images and audio in, text out |
Manufacturer data (announcement, model card), verified Oct 12, 2026.
Where we tested it
From the bottom up
TaskThe model had to answer 28 short questions on logic, space, theory of mind, calibration, and planning a text, each three times.
20 of 28 questions correct in all 3 attempts. It never got the cube with an unpainted bottom or the fourth word.
You'll find the size band and figures for other models on the Tested models page.