Get the latest tech news

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

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of RTX

RTX

Photo of setup

setup

Photo of Qwen

Qwen

Related news:

News photo

External Clock Generation on RTX 50 Series

News photo

China's fastest gaming GPU still falls far behind RTX 4060

News photo

Enabling Resizable Bar on RTX 3080 Vbios via GitHub