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

Re:RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 by varispeed on Saturday June 13, 2026 @12:29PM (#48518802)

Could 2x RTX5080 work just as well?

[ Parent | on HN ]

Re:RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 by iMil on Saturday June 13, 2026 @01:06PM (#48519188)

2xRTX5080 would be awesome. You'd only be able to run a q6, which it's already pretty good, but moreover you'd be able to use P2P and use Blackwell full speed, which I can't.

[ Parent | on HN ]

Re:RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 by kcb on Saturday June 13, 2026 @09:56PM (#48523435)

With 2 Blackwells, would make sense to run NVFP4 quants

[ Parent | on HN ]