This is why I love Zotac. We’ll, not this reason, but it adds to the small pile of smiles they’ve given me.
That being said I’m skipping this Nvidia gen and might break for AMD next. My 3090 is still trucking fine and I feel like Nvidia has lost their value after the debacles of the 40 series.
Did you hear about the news that AMD is skipping out on “high-end” market segment next generation? No real concrete numbers to this statement. I have heard speculation that they plan on making cards just as powerful as last gen except with better ray tracing and CHEAPER.
I have heard this, and to be honest, I don’t think I need the highest power GPU anymore. I mostly got the 3090 for VR and I seldom use my kit anymore. Upper-mid range AMD might be the answer for me.
You should think about selling it TBH. 3090 prices are shooting up like crazy, and may be at a peak, because they are the last affordable card to self host LLMs.
The 4090 is basically just as good as the 3090 because it has the same amount of vram, but twice the price… so you mind as well get 2x 3090s.
The 5090 will be hilariously expensive, and 24GB -> 32GB is not that great, as you still can’t run 70B class models in that pool… again, mind as well get 2x 3090s. I would not even bother trading my single 3090 for 5090.
If AMD sold a 48GB consumer card, you would see them dominate the open source LLM space in a month, because every single backend dev would buy one and get their projects working on them. Same with Intel. VRAM is basically the only thing that matters, and 24GB is kinda pitiful at a 4090’s price.
Halo has me hopeful that AMD are going to continue down this idea of having APUs that can use onboard RAM instead of requiring it to be built in. It’d be great to just be able to upgrade my RAM rather than replace a whole ass GPU.
Ut uses embedded LPDDR5X, so it will not be upgradeable unless the mobo maker uses LPCAMMs.
And… that’s kinda how it has to be. Laptop SO-DIMMs are super slow due to the design of the DIMMs, and they need crazy voltages to even hit the speeds/timings they run at now.
I’d already be happy if AMD goes with 24 GB on their upper midrange cards, but I would not be surprised if they stick with 16 GB. 48 GB seems extremely unlikely, unfortunately.
Doing LLMs with 8 GB is not fun, especially not with RDNA 2 which has so many issues with ROCm.
This is why I love Zotac. We’ll, not this reason, but it adds to the small pile of smiles they’ve given me.
That being said I’m skipping this Nvidia gen and might break for AMD next. My 3090 is still trucking fine and I feel like Nvidia has lost their value after the debacles of the 40 series.
Did you hear about the news that AMD is skipping out on “high-end” market segment next generation? No real concrete numbers to this statement. I have heard speculation that they plan on making cards just as powerful as last gen except with better ray tracing and CHEAPER.
I have heard this, and to be honest, I don’t think I need the highest power GPU anymore. I mostly got the 3090 for VR and I seldom use my kit anymore. Upper-mid range AMD might be the answer for me.
You should think about selling it TBH. 3090 prices are shooting up like crazy, and may be at a peak, because they are the last affordable card to self host LLMs.
Never even thought of that, is there a good website to sell a GPU on or is it pretty much just eBay?
I just don’t play games like I used to, just videos now. Poor thing hardly gets any use.
You could list it locally depending on where you are, through FB marketplace or Craigslist.
Otherwise, yeah, eBay.
Can’t you run LLMs on 4090/5090 maybe 5080? Basically any Nvidia card with 24GB+ of VRAM?
Yeah, but they not worth it.
The 4090 is basically just as good as the 3090 because it has the same amount of vram, but twice the price… so you mind as well get 2x 3090s.
The 5090 will be hilariously expensive, and 24GB -> 32GB is not that great, as you still can’t run 70B class models in that pool… again, mind as well get 2x 3090s. I would not even bother trading my single 3090 for 5090.
If AMD sold a 48GB consumer card, you would see them dominate the open source LLM space in a month, because every single backend dev would buy one and get their projects working on them. Same with Intel. VRAM is basically the only thing that matters, and 24GB is kinda pitiful at a 4090’s price.
Halo has me hopeful that AMD are going to continue down this idea of having APUs that can use onboard RAM instead of requiring it to be built in. It’d be great to just be able to upgrade my RAM rather than replace a whole ass GPU.
Ut uses embedded LPDDR5X, so it will not be upgradeable unless the mobo maker uses LPCAMMs.
And… that’s kinda how it has to be. Laptop SO-DIMMs are super slow due to the design of the DIMMs, and they need crazy voltages to even hit the speeds/timings they run at now.
I’d already be happy if AMD goes with 24 GB on their upper midrange cards, but I would not be surprised if they stick with 16 GB. 48 GB seems extremely unlikely, unfortunately.
Doing LLMs with 8 GB is not fun, especially not with RDNA 2 which has so many issues with ROCm.
skipping nvidia since gtx750ti, AMD all the way up
AMD is by far the price-per-unit-performance leader. Same is true on the CPU side. Intel and Nvidia aren’t even on the chart tbh.