logoalt Hacker News

kentm • today at 6:05 PM • 1 reply • view on HN

What are you using to host Qwen Flash Next right now?


Replies

atomicnumber3 • today at 7:16 PM

Unsloth studio, on a server that I built in 2024 that was, at the time, ludicrously oversized, but is now just ok-sized to run the q4 quant of qwen flash next. (128GB ram, 16GB vram).

I really want to build something less scuffed, but, yknow. So I'm making do atm.

➕ show 1 reply