Home | Notifications | New Note | Local | Federated | Search | Logout

Note Detail

Reply to @VD15@pl.valkyrie.world
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---
: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

---Replies---

Blurry Moon@sun@shitposter.world (2026-07-22 16:35:46)
@VD15 @theorytoe I have 256GB of unified RAM and I can't run the newest fucking models