10-09-2026, 05:10 AM
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
2x3090 • llama.cpp • too much VRAM is still not enough
|
multi-GPU offload advice: what are you seeing?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
multi-GPU offload advice: what are you seeing? - by visionyard23 - 10-07-2026, 12:31 AM
Re: multi-GPU offload advice: what are you seeing? - by bytesupply76 - 10-07-2026, 12:48 PM
Re: multi-GPU offload advice: what are you seeing? - by dockridge - 10-09-2026, 06:11 AM
Re: multi-GPU offload advice: what are you seeing? - by macroforge - 10-09-2026, 12:48 AM
Re: multi-GPU offload advice: what are you seeing? - by vrambandit - 10-09-2026, 05:10 AM
Re: multi-GPU offload advice: what are you seeing? - by dockriver - 10-09-2026, 07:17 AM
Re: multi-GPU offload advice: what are you seeing? - by pixelcrate82 - 10-09-2026, 11:58 AM
|
Users browsing this thread: 1 Guest(s)