AMD vs Nvidia

[humanpenguin@feddit.uk]

Blender supports cuda for much of its gpu work. It will work with amd. And there are projects allowing gpu rendering via amd. But they are (and have been for a while) a long way behind the cuda stuff.

For major rendering projects nvidia is still the fastest set up to use.

[user_naa@lemmy.world]

Does nouveau support RTX?

[that_leaflet@lemmy.world]

I had a better desktop experience with the FOSS driver than the proprietary driver when testing a 2060 on Fedora 41.

[korkki@lemmy.ml]

I haven't been on NVIDIA for a while so i couldn't tell for sure. I know that nvidia raytracing works on linux, but I'm not sure how it goes with the open drivers. If the noveau performance and stability is still somewhat lacking in general, then if both open drivers and raytracing are important to you then AMD is still the better bet.

[bluesquid0741@lemmy.sdf.org]

Is your information applicable to the nouveau drivers? I’d understood they’re many years behind in performance and capability but blender has never been in my use case.

[jul@discuss.tchncs.de]

Like others have already said, if you want Foss drivers then AMD is your only choice.

However, if you want the most performant cards on the market then you can safely choose nvidia. The drivers work really well now, even multi monitor vrr works now with the latest drivers.

Stop listening to what people are parroting, nvidia used to be a bad choice, but not anymore. Even Linus Torvalds has changed his mind

So, when AI people came in, that was wonderful, because it meant somebody at NVIDIA had got much more involved on the kernel side, and NVIDIA went from being on my list of companies who are not good to my list of people who are doing really good work.

[kusivittula@sopuli.xyz]

didn't know this. is it no good then? does it have the HDMI 2.1 driver missing from the open source driver?

[thorned_rose@sh.itjust.works]

Same, been using an AMD card since building a new PC a few years ago and its been completely smooth sailing. My spouse also built a new PC at the same time but decided to go nvidia instead and has had constant problems (now regrets not going AMD as well) and has yo regularly downgrade the driver and/or kernel just to have a working system or games that don't have things like vertices explosions.

[warmaster@lemmy.world]

I have 2 PCs, both on Linux. One with an AMD XTX 7900 XT, the other one has an Nvidia 3080 TI.

The Nvidia one is running the latest proprietary drivers, and they suck HARD. They just are far inferior to AMD's. The only reason to go Nvidia is to do local AI or video (editing / transcoding).

[lime@feddit.nu]

the driver is called AMDGPU PRO. it sits on top of the normal driver, and contains stuff specific to high performance compute. i think it's a requirement for properly fast ROCm but i'm not sure.

[covenant@sh.itjust.works]

Could be game specific, but there is no ground rendering in final fantasy. https://youtu.be/DxE-4ZxYxDA?si=ziYDWr5VAj7LV7hz

[umbrella@lemmy.ml]

if you are on linux AMD is the better choice, period.

don't get me wrong, nvidia will work relatively well, ive ran it before on linux. but it isnt worth the pricetag to have tons of small issues everywhere.

[shirro@aussie.zone]

AMD is by far the best choice for foss drivers. Intel might be an option in the future but I have no experience with their new cards. A second option would be good for Linux users but it's unlikely to be NVIDIA.

[gamechld@lemmy.world]

Honestly even on Windows I preferred AMD's software suite compared to Nvidia control panel and GeForce Experience. Currently using a 7900XTX and pretty happy with it. Also I missed Radeon Chill when I was on Nvidia, didn't expect to care about that at all, but I love it.

[eyedust@lemmy.dbzer0.com]

The only reason I still go Nvidia is because I self host AI, which afaik takes advantage of CUDA and just runs overall better on Nvidia cards, or at the very least is easier to set up. Really, the top reason is that it's the devil I know right now.

If I didn't self host AI, I would 100% go AMD. Especially if you don't want to use proprietary drivers. That being said, my old gaming laptop runs NixOS with Nouveau and there have definitely been improvements since I first tried it years ago, but I don't do much gaming on it. It's more a TV media station these days (so I can avoid the stupid smart TV bloat agenda, where your TV gets gradually slower and fits less increasingly-bloating apps over time).

[domi@lemmy.secnd.me]

If it's just about self-hosting and not training, ROCm works perfectly fine for that. I self-host DeepSeek R1 32b and FLUX.1-dev on my 7900 XTX.

You even get more VRAM for cheaper.

[eyedust@lemmy.dbzer0.com]

This is very good to know. I read that ROCm can be a pain to get up and running, but I read that months ago and this space is moving fast. I may switch over when I can if this is the case. My 3080 is feeling it's age already. Thank you!

[domi@lemmy.secnd.me]

That used to be the case, yes.

Alpaca pretty much allows running LLM out of the box on AMD after installing the ROCm addon in Discover/Software. LM Studio also works perfectly.

Image generation is a little bit more complicated.
ComfyUI supports AMD when all ROCm dependencies are installed and the PyTorch version is swapped for the AMD version.

However, ComfyUI provides no builds for Linux or AMD right now and you have to build it yourself.
I currently use a simple Docker container for ComfyUI which just takes the AMD ROCm image and installs ComfyUI ontop.

[eyedust@lemmy.dbzer0.com]

Definitely bookmarking this reply. I haven't tried ComfyUI yet, but I've had it starred on Github from back when it was fairly new. I'm no stranger to building from source, but I have not dived into Docker yet, which is becoming more and more of a weakness by the day. Docker is sometimes required by some really cool projects and I'm missing out.

[merthyr1831@lemmy.ml]

Both work, just in different ways. I think AMD's value proposition is better on Linux but if you were choosing between a 6700XT and a 4080 (for sake of example) of course the latter is still gonna be faster despite the drivers being a bit weirder to manage