Back to AIBriefs
How-ToDevelopers

RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8

Personal guide details a dual-GPU configuration (RTX 5080 + RTX 3090) to run Qwen 3.6 27B in Q8 quantization at over 80 tokens/s. Covers BIOS settings, PCIe splitting, and kernel driver setup for heterogeneous GPUs.

··Discuss
Jun 13, 9:55 AM
RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 — AIBriefs