[somewhatrandom9]

Could these quantized models make MTP (Multi-Token Prediction) significantly faster when used as drafters for larger regular Gemma 4 models?

[dist-epoch]

Google already released specialized drafters for Gemma 4.

[Havoc]

The E2B ones? Or what do you mean by specialized drafters?

[int_19h]

They have -assistant in the name, so e.g.: https://huggingface.co/google/gemma-4-31B-it-assistant

[Havoc]

Thanks

[girvo]

The “-assistant” models released by Google are specialised tiny MTP draft models :)

31b-it-assistant is what enables MTP