Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

theverge.com

Post reply on HN
Print view View original

171–180 of 776 posts

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#171

Post by topherjaynes »

lemoncookiechip wrote: post #159

I have a feeling regular consumers will have trouble buying 5090s. RTX 5090: 32 GB GDDR7, ~1.8 TB/s bandwidth. H100 (SXM5): 80 GB HBM3, ~3+ TB/s bandwidth. RTX 5090: ~318 TFLOPS in ray tracing, ~3,352 AI TOPS. H100: Optimized for matrix and tensor computations, with ~1,000 TFLOPS for AI workloads (using Tensor Cores). RTX 5090: 575W, higher for enthusiast-class performance. H100 (PCIe): 350W, efficient for data cente…

That's my worry too, I'd like one or two, but 1) will either never be in line for them 2) or can only find via secondary market at 3 or 4x the price...

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#172

Post by boroboro4 »

lemoncookiechip wrote: post #159

I have a feeling regular consumers will have trouble buying 5090s. RTX 5090: 32 GB GDDR7, ~1.8 TB/s bandwidth. H100 (SXM5): 80 GB HBM3, ~3+ TB/s bandwidth. RTX 5090: ~318 TFLOPS in ray tracing, ~3,352 AI TOPS. H100: Optimized for matrix and tensor computations, with ~1,000 TFLOPS for AI workloads (using Tensor Cores). RTX 5090: 575W, higher for enthusiast-class performance. H100 (PCIe): 350W, efficient for data cente…

H100 has 3958 TFLOPS sparse fp8 compute. I’m pretty sure listed tflops for 5090 are sparse (and probably) fp4/int4.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#174

Post by KMnO4 »

ryao wrote: post #97
ziml77 wrote: post #55

Earlier quoted context omitted.

The 4090 already seemed positioned as a card for consumer AI enthusiast workloads. But this $1000 price gap between the 5080 and 5090 seems to finally cement that. Though we're probably still going to see tons of tech YouTubers making videos specifically about how the 5090 isn't a good value for gaming as if it even matters. The people who want to spend $2000 on a GPU for gaming don't care about the value and everyon…

If I recall correctly, the 3090, 3090 Ti and 4090 were supposed to replace the Titan cards that had been Nvidia's top gaming cards, but were never meant for gaming.

Someone very clever at Nvidia realized that if they rename their professional card (Titan) to be part of their "gaming" line, you can convince adults with too much disposable income that they need it to play Elden Ring.

I didn't know of anyone who used the Titan cards (which were actually priced cheaper than their respective xx90 cards at release) for gaming, but somehow people were happy spending >$2000 when the 3090 came out.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#175

Post by logicalfails »

geertj wrote: post #173

Any advice on how to buy the founders edition when it launches, possibly from folks who bought the 4090 FE last time around? I have a feeling there will be a lot of demand.

Getting a 3080 FE (I also had the option to get the 3090 FE) at the height of pandemic demand required me sleeping outside a Best Buy with 50 other random souls on a wednesday night.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#176

Post by nullandvoid »

wruza wrote: post #151
jsheard wrote: post #4

32GB of GDDR7 at 1.8TB/sec for $2000, best of luck to the gamers trying to buy one of those while AI people are buying them by the truckload. Presumably the pro hardware based on the same silicon will have 64GB, they usually double whatever the gaming cards have.

Why do you need one of those as a gamer? 1080ti was 120+ fps in heavy realistic looking games. 20xx RT slashed that back to 15 fps, but is RT really necessary to play games? Who cares about real-world reflections? And reviews showed that RT+DLSS introduced so many artefacts sometimes that the realism argument seemed absurd. Any modern card under $1000 is more than enough for graphics in virtually all games. The gamin…

Many people are running 4k resolution now, and a 4080 struggles to to break 100 frames in many current games maxed (never-mind future titles) - therefore there's plenty of a market with gamers and the 5x series (myself included) who are looking for closer to 4090 performance at a non obscene price.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#177

Post by me551ah »

wruza wrote: post #151
jsheard wrote: post #4

32GB of GDDR7 at 1.8TB/sec for $2000, best of luck to the gamers trying to buy one of those while AI people are buying them by the truckload. Presumably the pro hardware based on the same silicon will have 64GB, they usually double whatever the gaming cards have.

Why do you need one of those as a gamer? 1080ti was 120+ fps in heavy realistic looking games. 20xx RT slashed that back to 15 fps, but is RT really necessary to play games? Who cares about real-world reflections? And reviews showed that RT+DLSS introduced so many artefacts sometimes that the realism argument seemed absurd. Any modern card under $1000 is more than enough for graphics in virtually all games. The gamin…

> Any modern card under $1000 is more than enough for graphics in virtually all games

I disagree. I run a 4070 Super, Ryzen 7700 with DDR5 and I still cant run Asseto Corsa Competizione in VR at 90fps. MSFS 2024 runs at 30 something fps at medium settings. VR gaming is a different beast

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#178

Post by mastax »

kllrnohj wrote: post #150
diggan wrote: post #137

Earlier quoted context omitted.

> modern games + modern cards can't even do 4k at high fps What "modern games" and "modern cards" are you specifically talking about here? There are plenty of AAA games released last years that you can do 4K at 60fps with a RTX 3090 for example.

> There are plenty of AAA games released last years that you can do 4K at 60fps with a RTX 3090 for example. Not when you turn on ray tracing. Also 60fps is pretty low, certainly isn't "high fps" anyway

> Also 60fps is pretty low, certainly isn't "high fps" anyway

I’m sure some will disagree with this but most PC gamers I talk to want to be at 90FPS minimum. I’d assume if you’re spending $1600+ on a GPU you’re pretty particular about your experience.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#179

Post by terhechte »

blixt wrote: post #156

Pretty interesting watching their tech explainers on YouTube about the changes in their AI solutions. Apparently they switched from CNNs to transformers for upscaling (with ray tracing support) if I understood correctly though for frame generation makes even more sense to me. 32 GB VRAM on the highest end GPU seems almost small after running LLMs with 128 GB RAM on the M3 Max, but the speed will most likely more than…

If you have 128gb ram, try running MoE models, they're a far better fit for Apple's hardware because they trade memory for inference performance. using something like Wizard2 8x22b requires a huge amount of memory to host the 176b model, but only one 22b slice has to be active at a time so you get the token speed of a 22b model.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#180

Post by rane »

wruza wrote: post #151
jsheard wrote: post #4

32GB of GDDR7 at 1.8TB/sec for $2000, best of luck to the gamers trying to buy one of those while AI people are buying them by the truckload. Presumably the pro hardware based on the same silicon will have 64GB, they usually double whatever the gaming cards have.

Why do you need one of those as a gamer? 1080ti was 120+ fps in heavy realistic looking games. 20xx RT slashed that back to 15 fps, but is RT really necessary to play games? Who cares about real-world reflections? And reviews showed that RT+DLSS introduced so many artefacts sometimes that the realism argument seemed absurd. Any modern card under $1000 is more than enough for graphics in virtually all games. The gamin…

1080ti is most definitely not powerful enough to play modern games at 4k 120hz.
Post reply on HN