Well, it was nice ... having hope, I mean. That was a good feeling.
this post was submitted on 14 Feb 2025
40 points (100.0% liked)
LocalLLaMA
2795 readers
2 users here now
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
So? Are you saying that you are pot committed 3 cards in? How many cards do you run in each rig?
If half the price can't convince you, you aren't ready to switch no matter what.
Fair enough. I've got a 3060 and 4060ti installed, and I need to buy a new PSU to power up a 1080ti externally.
I think the only thing I use that requires CUDA is Daz Studio, and I'm actually starting to lose interest in that.
The thing about Radeon is it's not just less money, it's also less performance, plus more work to set up. I bought a Radeon laptop just so I could try ROCm. It works, but it's no walk in the park. And when you're done, you don't get any benefit over using Nvidia. If AMD at least gave us more VRAM, that would be something.