1
RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8
Dual GPU setup: run Qwen 3.6 27B at a Q8 quantization at 80+ tokens/sec with 39GB total VRAM
Visit imil.net → On Hacker News Jul 2019 – Jun 2026
Systems & Performance 2Hardware & Electronics 1AI & Machine Learning 1
Dual GPU setup: run Qwen 3.6 27B at a Q8 quantization at 80+ tokens/sec with 39GB total VRAM