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

New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

nvidia.com

Post reply on HN
Print view View original

51–60 of 135 posts

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#51

Post by throwup238 »

pixelpoet wrote: post #49
throwup238 wrote: post #37

Earlier quoted context omitted.

The two parent 2080s were lost in a tragic cryptocurrency mining accident when the bitcoin ceiling collapsed. Please send donations to the Aboveground Miners fund in your choice of shitcoin.

I get that it's supposed to be funny, but I wonder how many people still think bitcoin mining happens on GPUs, particularly Nvidia ones. Pretty sure that stopped being the case like 14 years ago or something? Anyway...

ASICs didn’t really take over until around 2013 (I was designing some PCBs for one of the first ASICs in 2012)

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#52

Post by BaculumMeumEst »

eurekin wrote: post #40
michaelt wrote: post #31

Earlier quoted context omitted.

My impression is a lot of the open source action is around the just-about-runs-in-12GB region - lots of models coming out with 7B/13B and 4-bit quantisation, a few 70B models (which won't fit in 24GB anyway) and only limited stuff in between. I suppose I could be getting a biased impression though, as of course many more people are in a position to recommend the more accessible models. What sort of things are you run…

As the ancestor commenter mentioned: > If you’re interested in ML training Training - at least the one I tried - requires to be run in fp16 mode. So a 7b net needs 14 GB for the model weights alone, plus some extra for the context and the stuff I don't really understand (some gradient values, oh that makes sense now that I've written it)

using cloud hardware for training and consumer cards for inference seems like the common sense thing to do then

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#53

Post by paulmd »

pixelpoet wrote: post #49
throwup238 wrote: post #37

Earlier quoted context omitted.

The two parent 2080s were lost in a tragic cryptocurrency mining accident when the bitcoin ceiling collapsed. Please send donations to the Aboveground Miners fund in your choice of shitcoin.

I get that it's supposed to be funny, but I wonder how many people still think bitcoin mining happens on GPUs, particularly Nvidia ones. Pretty sure that stopped being the case like 14 years ago or something? Anyway...

Litecoin and Doge and Ethereum were mined on GPUs throughout that period. And in fact all the other coins are tied to bitcoin in the first place, bitcoin price runs also trigger huge mining booms in everything else, so yeah, it's kinda understandable that people tend to view them as a single linked thing, because they kinda are.

What, precisely, is the point of making "actually you mean crypto, not bitcoin" posts, other than demonstrating that you are, indeed, "very smart"? Like, this person doesn't even exist, it's just a "heh aren't those no-coiners dumb" strawperson that you imagine to be some big dummy.

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#54

Post by schaefer »

deepsquirrelnet wrote: post #41
woodson wrote: post #7

If you’re interested in ML training, to save you some time, RTX 4080 Super and RTX 4070 Ti Super have 16GB GDDR6X, the RTX 4070 Super has 12GB.

It seems they’re being very careful not to undercut their enterprise offerings or even the 4090. Assuming they’re not completely tone deaf, I can only assume this is the explanation.

The Jetson AGX Orin Developer Kit [1] has 64 GB of unified 256-bit LPDDR5 memory.

It costs $2,000 and might get some people someplace interesting.

[1]: https://developer.nvidia.com/embedded/learn/getting-started-...

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#55

Post by newsclues »

laweijfmvo wrote: post #3

> All three GeForce RTX 40 SUPER Series GPUs are faster than their predecessors It's weird that they're only comparing the new cards to the RTX 30's and 20's, and not the "v1" 40's. I assume the 4080 SUPER is faster than the 4080 (based on name?) but it seems cheaper and there's absolutely no comparison data

Most people don’t upgrade to the same generation super card.

Most people upgrade from a 10, 20 or less so 30 series card.

They are selling upgrades to older generations.

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#56

Post by eurekin »

BaculumMeumEst wrote: post #52
eurekin wrote: post #40

Earlier quoted context omitted.

As the ancestor commenter mentioned: > If you’re interested in ML training Training - at least the one I tried - requires to be run in fp16 mode. So a 7b net needs 14 GB for the model weights alone, plus some extra for the context and the stuff I don't really understand (some gradient values, oh that makes sense now that I've written it)

using cloud hardware for training and consumer cards for inference seems like the common sense thing to do then

In the spirit of hackernews, one can also build a rig such as this one:

https://nonint.com/2022/05/30/my-deep-learning-rig/

and land a job at OpenAI as a side effect. Of all places, I wasn't expecting such pushback here

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#57

Post by newsclues »

notJim wrote: post #17
selectodude wrote: post #10

Earlier quoted context omitted.

They’re trying to sell to me, the owner of a fully orphaned 3070 with a measly 8GB of vram. Not a current 40 series owner.

What does orphaned mean in this context?

Less desirable because vram has become more important.

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#58

Post by paulmd »

michaelt wrote: post #31
baobabKoodaa wrote: post #18

Earlier quoted context omitted.

With the current generation of text and image generators, 24GB is the sweet spot

My impression is a lot of the open source action is around the just-about-runs-in-12GB region - lots of models coming out with 7B/13B and 4-bit quantisation, a few 70B models (which won't fit in 24GB anyway) and only limited stuff in between. I suppose I could be getting a biased impression though, as of course many more people are in a position to recommend the more accessible models. What sort of things are you run…

with both you and GP, I would imagine the answer is that people tend to build models to the hardware that is available. If 12GB and 24GB are the hardware thresholds that people have, you'll get "open-source action" in the 12GB and 24GB models, because people want to build things that run on the hardware they own.

(Which is of course how CUDA built its success more generally, vs the "you have to buy the $5k workstation card to get started" strategy from ROCm.)

More generally you'd call this optimization and targeting the hardware that's available. No sense releasing crysis when everyone is running a commodore 64, after all.

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#59

Post by LUmBULtERA »

y-c-o-m-b wrote: post #27

My 3080 laptop GPU can still play 99% of games at their highest settings. Or at least they did before the latest batch of nVidia drivers went to shit. It's not the hardware that's the problem. What's the point of upgrading to a 4-series when we're left with stuttering and defects from software issues? EDIT: even people on the 4-series are experiencing it https://www.nvidia.com/en-us/geforce/forums/game-ready-drive...

There isn't usually much point in upgrading one generation in most hardware products. Typically that's wasteful in all but edge-use cases.

Re: New GeForce RTX 4080 Super, RTX 4070 Ti Super, RTX 4070 Super

#60

Post by glonq »

Ekaros wrote: post #43
eurekin wrote: post #13

Earlier quoted context omitted.

Thanks! That rules them out completely EDIT: For training

Very good. Maybe as a gamer I can get one eventually for reasonable price.

Depending on your definition of 'reasonable', that ship sailed a few years ago and ain't ever coming back
Post reply on HN