2026-09-15 09:35 UTC
Who can afford the hardware to run an open weight model? We aren’t all earning enough to afford high end NVIDIA cards (when they’re even available).
Replies (4)
-
@schnurrito@discuss.tchncs.de 2026-09-15 09:56
I’ve done it at my job.
-
@Johanno@feddit.org 2026-09-15 10:11
If you consider what companies pay for the subscription you will see that the hardware prices aren’t really the issue here.
-
@sockenklaus@sh.itjust.works 2026-09-15 10:38
You may be overestimating the hardware requirements for current open weights. I am running Qwen3.8-27b with 52.000 tokens context on a RX 7900 XTX from 2022 with 15 - 30 tokens / second. Sure, it was a high end card back then but for a graphics card today it’s quite affordable when you’re looking for a used one. Also it’s not blazingly fast, but it gets the job done.
-
@surewhynotlem@lemmy.world 2026-09-15 10:59
I run my models on a 1070. It’s slow but works.