News for hackers. Stuff that matters.
Re:Llama.cpp AI Performance with the GeForce RTX 5090 Review by zamadatix on Monday March 10, 2025 @10:06AM (#43320794)
3090, the 24 GB of VRAM will be more relevant than running smaller models even faster on lower capacity card (small models already run fast by nature of being less to copy from memory and compute on).

There are no comments on this comment yet.