BLAST RADIUS

Open-weight & owned stack · Training tuning

BottleCap Releases ThinkingCap Qwen Model Weights

Sep 24, 2026, first seen via MarkTechPost

BottleCap AI released gated ThinkingCap-Qwen3.8-27B weights claiming 37.2% fewer thinking tokens for a 0.86-point accuracy cost.

Read the original at marktechpost.comOpens the publisher's site in a new tab

Also covering this

BottleCap AI Releases ThinkingCap-Qwen3.8-27B: 37.2% Fewer Thinking Tokens at a 0.86pp Accuracy Cost - MarkTechPostmarktechpost.com, Sep 24

More in Open-weight & owned stack

Kyutai Releases Voice Of Reason CheckpointsSep 23Xiaomi Releases MiMo-V2.6 Open-Weight Model FamilySep 22Intrinsic open-sources Core robotics software infrastructureSep 22Harvey Launches Kimi-Based In-House ModelSep 21Kimi K3 Reaches AWS And Alibaba Cloud PlatformsSep 21