NVIDIA GeForce RTX 3070

I think that speaks to them not understanding at the time the opportunity they were missing out on by not shipping a CUDA-like thing to everyone, including consumer tech. The question is what'll it look like in a few years now that they do understand AI is the biggest part of the GPU industry. I suspect, given AMDs relative openness vs. nvidia, even consumer-level stuff released today will end up with a longer useful life than current nvidia stuff. I could be wrong, of course. I've taken the gamble...the last nvidia GPU I bought was a 3070 several years ago. Everything recent has been AMD. It's half the price for nearly competitive performance and VRAM. If that bet turns out wrong, I'll just upgrade a little sooner and still probably end up ahead. But, I think/hope openness will win. Also, nvidia graphics drivers on Linux are a pain in the ass that I didn't want to keep dealing with. I decided it wasn't worth the hassle, even if they're better on some metrics. I've been able to run everything I've tried on an AMD Strix Halo and an old Radeon Pro V620 (not great, but cheap, compared to other 32GB GPUs and still supported by current ROCm).

> my tower with an Nvidia 3000 series card was considerably more troublesome with it. I think you're describing a driver error from before Nvidia really supported Wayland. My 3070 exhibited similar behavior but was fixed with the 555-series drivers. The Vulkan drivers are still so/so in terms of performance, but the smoothness is now on-par with my Macbook and Intel GNOME machine.

I’ve been running CachyOS with Hyprland on my RTX3070 with no glaring issues. But eventually I plan to switch to a Radeon card.

You're basically confirming the parent's suspicions. Nvidia has supported Wayland since their 550 series drivers, for the last two years desktop Linux has run fine on damn near every supported card. You're not speaking for the "average user" here, you're speaking for yourself. We have a benchmark for what the average user thinks about Linux, and it's called a Steam Deck. You know what those users never mention? X11, Wayland, Xwayland or any of the stereotypical 2012-era boogeymen you're complaining about. It's almost as if... you haven't used Linux in years. I won't accuse you outright, but my suspicions are mounting. (posted from an RTX 3070 on Wayland)

>I spent a ton of time trying to get Chatterbox to work (on Debian Linux 13) Exactly my case. I had to move back to Debian from Ubuntu, where I had installed Chatterbox without much difficulty, and it was hell. You pretty much need Anaconda. With it, it's a cinch. >what are open-source voice synth which have been working for you. I tried a few, although rather superficially. Keeping in mind that my 3090 is on my main (Windows) machine, I was constrained to what I could get running on it without too much hassle. Considering that: * I tried Parler for a bit, although I became disillusioned when I learned all models have an output length limit, rather than doing something internally to split the input into chunks. What little I tried with it sounded pretty good if it stayed within the 30-second window, otherwise it became increasingly (and interestingly) garbled. * Higgs was good. I gave it one of Senator Armstrong's lines and made it generate the "mother of all omelettes" one, and it was believable-ish; not as emphatic but pretty good. But it was rather too big and slow and required too much faffing around with the generation settings. * Chatterbox is what I finally settled with for my application, which is making audiobooks for myself to listen to during my walks and bike rides. It fits in the 3070 I have on the Linux machine and it runs pretty quick, at ~2.7 seconds of audio per second. These are my notes after many hours of listening to Chatterbox: * The breathing and paus…

I have an RTX 3070 with 8GB VRAM and for me Qwen3:30B-A3B is fast enough. It's not lightning fast, but more than adequate if you have a _little_ patience. I've found that Qwen3 is generally really good at following instructions and you can also very easily turn on or off the reasoning by adding "/no_think" in the prompt to turn it off. The reason Qwen3:30B works so well is because it's a MoE. I have tested the 14B model and it's noticeably slower because it's a dense model.

I remember building an Ahtlon 64 system with a GeForce 7900GTX at that time and I played with Far Cry everything maxed out. Half of the cost of that computer was the graphics card and it was the absolute highest end model that money could buy. Recently I bought a graphics card for 600 when the prices came down, a 3070 RTX, a more conservative choice since the top models now go for 2k.

As someone who owns an RTX 3070, why is it so special? I've found myself wishing I had the 3060 Ti for the 12gb memory, sometiemes.

>You could at least give an example. You claimed that AMD can’t make software, full stop. That’s not a fair analysis. * AMD straight up does not provide assistive tooling for 7900X3D and 7950X3D's asymmetric cores, this has meant worse performance than the lower tier 7800X3D that doesn't need such tooling. This is in stark contrast to Intel with Intel Thread Director that provides assistance to the OS scheduler (Windows 11 and Linux 5.18 and up). * Just one[1] of many more examples I can't bothered to keep track of. Also a piece of anecdata, a close friend of mine moved to Nvidia from AMD last year because he was fed up with problems involving his streaming setup which all stemmed from the AMD drivers; he hasn't had problems since switching. This isn't to say Nvidia's drivers are flawless, but overall there definitely seem to be more problems with AMD than Nvidia. * The "AI" world can also tell you all about how AMD simply does not grok software. Nvidia is the overlord of "AI" in large part because AMD simply does/can not software. [1]: https://community.amd.com/t5/drivers-software/elite-dangerou... >I like how I don’t have the ugly 1990s Nvidia control panel anymore. I would argue that's a feature, using a GUI language (Windows Explorer) that is well defined and based on solid research and real feedback. >I also like how I don’t have to login to an account for automatic driver updates like I did with the GeForce Experience application. Drivers are absolutely not something…

So you’re saying I could make the full model run on a 16 core ryzen with 64GB of DDR4? I have an 8GB VRAM 3070 but based on this thread it sounds like the CPU might have better perf due to the RAM?