Home | Notifications | New Note | Local | Federated | Search | Logout
Note Detail
Reply to @theorytoe@ak.kyaruc.moe
:VD15_0::VD15_1::VD15_2::VD15_3::VD15_4::VD15_5::VD15_6::VD15_7:@VD15@pl.valkyrie.world (2026-07-22 16:25:07)
@theorytoe I used to run locally until torch dropped support for the cards I was using and I couldn't be fucked having a jet engine under my desk anymore. I'm on a pay-as-you-go plan for API access now but I still only use open weight models
---Reply---
alle_yoj813@theorytoe@ak.kyaruc.moe (2026-07-22 16:29:38)
@VD15 ok
I was looking into some of the stats required to run these models (mainly glm) and holy shit its a lot
Reply
---Replies---
:VD15_0::VD15_1::VD15_2::VD15_3::VD15_4::VD15_5::VD15_6::VD15_7:@VD15@pl.valkyrie.world (2026-07-22 16:33:35)
@theorytoe Yeah, I thought 72GB of VRAM was a lot back when llama was all the rage and then deepseek came out and I was like HOW MUCH!?
I ain't willing to spend the equivalent of a new car on GPUs rn