vlm.fyi Get the data
Models / Google

Gemma 4 31B

Measured on 1 provider. The model card lists image, text, video input; what each provider accepts is below.

Jarvislabs

gemma-4-31b-it
Images
4 “The model rejected the request parameters.”
768×432 frames
4 “The model rejected the request parameters.”
Tokens / frame
1,110
Inline body
12 MB “Request body exceeds the byte limit.”
Images by URL
≥ 128 MB
Video file
256 MB “The model rejected the request parameters.”
Video tok/min
467
Frames/min
6.2 ⁎
Video input
Yes
Tool messages
Lenient
Extra fields
All accepted
  • The deployment accepts at most 4 images per request.

Measured 2026-10-31