Show HN: Kvark Sparkle 27B – reasoning model trained to think with fewer tokens
By Archelunch · 2026-11-02 · 1 points · 0 comments
https://huggingface.co/Egzakta/Kvark-Sparkle-1.0-27B
We had problems with Qwen spending too much time reasoning about tasks instead of doing them. That's why we decided to fine-tune it to use fewer reasoning tokens without losing accuracy. After a bunch of experiments we ended up with KVARK Sparkle 27B. On our evaluations it uses…
Open the full discussion on BetterNews