Qwen 3.6 27B performance reported on NVIDIA RTX 5090
The Qwen 3.6 27B model achieves 80-100 t/s on an RTX 5090, dropping to 40 t/s at its 262k context limit. The model fits within the GPU's memory without vision capabilities enabled.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Claude Code 2.1.227 fixes subscription-tier, Bash and TUI bugs
- Curated resources for the open Agent2Agent protocol
- Suno to cap song downloads to curb AI slop
- Claude Code plugin translates 'Claudish' output into plain English
- Claude Code v2.1.227 fixes flag evaluation and Bash command failures