Bottlecap AI Blog company blog
Gemma-4-26B-A4B with 39-69% less thinking at same accuracy
This 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.
- Points
- 127
- HN comments
- 34
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSoftware Engineering2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 23, 2026 | Gemma-4-26B-A4B with 39-69% less thinking at same accuracy by armcat | 127 | 34 |
