File size: 633 Bytes
04e4894
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
Gemma 4 31B is provided under the Gemma Terms of Use.

These Core AI (.aimodel) bundles are a format conversion of the weights from
google/gemma-4-31B-it-qat-q4_0-unquantized and remain governed by Google's Gemma
license. By downloading or using these files you agree to the Gemma Terms of Use.

  Gemma Terms of Use:        https://ai.google.dev/gemma/terms
  Prohibited Use Policy:     https://ai.google.dev/gemma/prohibited_use_policy

The conversion itself (the Core AI bundles and the custom Metal flash-decode SDPA
kernel that lets the model run on the engine) imposes no additional restrictions
beyond the Gemma Terms of Use.