§ feed · storyline

BottleCap AI Releases ThinkingCap-Qwen3.8-27B

BottleCap AI releases ThinkingCap-Qwen3.8-27B, a fine-tuned model that cuts reasoning tokens by 37.2% with minimal accuracy trade-off.

Sep 24 · 02:00:00 · primary fetch1 sourceupdated Sep 24 · 02:00:00

BottleCap AI released ThinkingCap-Qwen3.8-27B, a fine-tuned model focused on reducing reasoning tokens by 37.2% with a minimal accuracy trade-off.

§ sources1 publication · timeline below