ThinkingCap: Gemma-4-26B-A4B — up to 69% and on average 39% less thinking, at unchanged accuracy
- TL;DRThis is the fifth model in the ThinkingCap series.
- We reduced how much Google's gemma-4-26B-A4B-it thinks, without compromising the quality of its answers.
Unverified
- TL;DRThis is the fifth model in the ThinkingCap series.
- We reduced how much Google's gemma-4-26B-A4B-it thinks, without compromising the quality of its answers.
Sources: Bottlecapai