Skip to content
v0.7.7
James's avatar
James
@james
bc520bca · fix(inference): disable Qwen3.5-0.8B thinking loops ·
Release: v0.7.7 
v0.7.7

- fix local Qwen/Qwen3.5-0.8B chat so text and image prompts default to non-thinking mode under llama.cpp
- stop runaway reasoning output that made local replies look stuck or image-blind