NVIDIA 4000 Series

[Bencher]

next gen nvidia is going for the kill, they will obliterate amd so that they can exclusively focus on core markets like custom ASICs for OEMs like Sony, MS, Valve etc.. atleast thats what the markets are predicting in the form of glorious financial projections for nvidia

Isn't that already the case? AMD can only compete on price, basically by being cheaper.

 

[Armageus]

Table created to visualise the BS

	Model	Die	CUDA Cores	Memory Bus (bits)	Bandwidth (GB/s)	VRAM (GB)	TDP (W)	Price
Mobile	4050 Laptop	AD107	2560	96		6	35-115
Mobile	4060 Laptop	AD107	3072	128		8	35-115
Mobile Workstation	RTX 2000 ADA	AD107	3072	128		8	35-140
Desktop	4060	AD107	3072	128	272	8	115	$299
Desktop	4060Ti	AD106	4352	128	288	8/16	160	$399/$499
Mobile	4070 Laptop	AD106	4608	128		8	35-115
Mobile Workstation	RTX 3000 ADA	AD106	4608	128	256	8	35-140
Theoretical	AD106 Max	AD106	4608	128
Fake/Leak	4060 Super		5120	192	432	12	200	$399
Mobile Workstation	RTX 3500 ADA	AD104	5120	192	432	12	60-140
Desktop	4070	AD104	5888	192	504.2	12	200	$599
Workstation	RTX 4000 SFF ADA	AD104	6144	160	320	20	70
Mobile	4080 Laptop	AD104	7424	192		12	80-150
Mobile Workstation	RTX 4000 ADA	AD104	7424	192	432	12	80-175
Desktop	4070 Ti	AD104	7680	192	504.2	12	285	$799
Datacenter	L4	AD104	7680	192	504.2	24	285
Theoretical	AD104 Max	AD104	7680	192
Fake/Leak	4070 Super		8192	256	672	16	280	$699
Mobile	4090 Laptop	AD103	9728	256		16	80-150
Mobile Workstation	RTX 5000 ADA	AD103	9728	256		16	80-175
Desktop	4080	AD103	9728	256	761.8	16	320	$1199
Theoretical	AD103 Max	AD103	10240	256
Fake/Leak	4080 Super		13312	320	840	20	350	$1199
Desktop	4090	AD102	16384	384	1008	24	450	$1599
Datacenter	L40	AD102	18176	384	864	24/48	300
Workstation	RTX 6000 ADA	AD102	18176	384	960	48	300
Theoretical	AD102 Max	AD102	18432​	384
Fake/Leak	4090 Super		18432​	384	1152	24	450	$1999

Only one that makes a semblance of sense is the 4060 Super, as there has already been a cut down AD104 die with those specs made (for the RTX 3500 ADA Mobile part)


(4090 Super is definitely a no go if even the Datacenter parts are leaving CUDA cores unused likely due to yields. 4070 Super and 4080 Super just seem like too significant cuts of the dies used, to be economically viable, unless yields are really that bad)

 

[SpellowHouse]

next gen nvidia is going for the kill, they will obliterate amd so that they can exclusively focus on core markets like custom ASICs for OEMs like Sony, MS, Valve etc.. atleast thats what the markets are predicting in the form of glorious financial projections for nvidia

I am not sure the markets care about the PC. They are far more interested in AI - which seems to be this months "thing to invest in".

 

[brostradamus]

I am not sure the markets care about the PC. They are far more interested in AI - which seems to be this months "thing to invest in".

its not just prices, equity researchers have built in obscene amounts into future fundamental performance.. here's data from a market aggregator, look at the revenue and EBITDA development.. though data sourced from bloomberg would be more reliable

NVIDIA Corporation (NVDA) Stock Price | Stock Quote Nasdaq - MarketScreener

NVIDIA Corporation (NVDA.NASDAQ): Stock quote, stock chart, quotes, analysis, advice, financials and news for Stock NVIDIA Corporation | Nasdaq: NVDA | Nasdaq

www.marketscreener.com

 

[Dicehunter]

its not just prices, equity researchers have built in obscene amounts into future fundamental performance.. here's data from a market aggregator, look at the revenue and EBITDA development.. though data sourced from bloomberg would be more reliable

Yeah but listen to this... your username is total bro'ness, Righteously dude approved !

 

[Lightnix]

Only one that makes a semblance of sense is the 4060 Super, as there has already been a cut down AD104 die with those specs made (for the RTX 3500 ADA Mobile part)


(4090 Super is definitely a no go if even the Datacenter parts are leaving CUDA cores unused likely due to yields. 4070 Super and 4080 Super just seem like too significant cuts of the dies used, to be economically viable, unless yields are really that bad)

Didn't know about that RTX3500 Ada mobile part to be fair, does make it sound a little more plausible.

But then for what Nvidia charges for workstation level parts they probably could have stuck an AD103 in there and still had a healthy margin so not sure that it's likely to be reflected in consumer desktop parts any time soon.

Great table.

 

[RavenXXX2]

Is there any chance he's actually right or just making stuff up for clicks ?

https://twitter.com/i/web/status/1666070716515491841

 

[SpellowHouse]

its not just prices, equity researchers have built in obscene amounts into future fundamental performance.. here's data from a market aggregator, look at the revenue and EBITDA development.. though data sourced from bloomberg would be more reliable

NVIDIA Corporation (NVDA) Stock Price | Stock Quote Nasdaq - MarketScreener

NVIDIA Corporation (NVDA.NASDAQ): Stock quote, stock chart, quotes, analysis, advice, financials and news for Stock NVIDIA Corporation | Nasdaq: NVDA | Nasdaq

www.marketscreener.com

 

[Jay85]

God damn AMD do something!

 

[Lightnix]

God damn AMD do something!

AMD: "you mean a massive **** off data centre APU? We got you"

AMD Instinct MI300 to be first generation exascale APU with Zen4 CPU and CDNA3 GPU - VideoCardz.com

One of the Instinct MI300 products could be AMD’s first exascale APU Earlier this month, we learned that Instinct MI300 product family from AMD will launch in many forms. This first CDNA3-based product would feature 3D stacking technology that allows AMD to provide various configurations to...

videocardz.com

 

[Brackish]

All this AI data centre stuff will probably be used to promote the next gen games with "superior AI" and "Free thinking NPC's"

 

[SpellowHouse]

All this AI data centre stuff will probably be used to promote the next gen games with "superior AI" and "Free thinking NPC's"

5090 plays the game for you, so you can get out and have a real life and ONLY costs £3000

 

[Brackish]

5090 plays the game for you, so you can get out and have a real life and ONLY costs £3000

And as an added extra for paying the extra add-on fee for DLSS 5.0 you get a remake of the classic Altered Beast game from the Sega days, on GeForce now which requires a subscription.

Thinking about it, it's all about subscription services, not just NV but from media, lease cars (like a subscription) would we ever see one of the GPU makers start a subscription service for their GPU's?

 

[JediFragger]

God damn AMD do something!

AMD don't even have the software engineers to utilise/develop for the AI-upscale that's built into the rDNA3 architecture!!!! It's been stated that they aren't going to (not from an official source). I'm hoping that's wrong because it's *dire* if so!

****ing pathetic.

 

[danlightbulb]

would we ever see one of the GPU makers start a subscription service for their GPU's?

It could work.

4090 for £1500. Resale price after two years £800, so £700 to pay over 24 months is £30 a month.

It worked for phones, although you pay the whole phone off over the contract, I'd be more interested in the above model where you only pay half.

 

[Troezar]

It could work.

4090 for £1500. Resale price after two years £800, so £700 to pay over 24 months is £30 a month.

It worked for phones, although you pay the whole phone off over the contract, I'd be more interested in the above model where you only pay half.

You know they would charge you £50 and keep the rest for profit

 

[Grim5]

Overclockers hope to get close to mythical 4ghz barrier with new Strix 4090

ASUS GeForce RTX 4090 ROG MATRIX PCB Dissected: Similar To STRIX With Added Functions & Less Coil Whine

The recently revealed ASUS ROG Matrix RTX 4090 has been subjected to a thorough PCB review courtesy of the renowned reviewer Der8auer.

wccftech.com

 

[mrk]

Pointless^


Nvidia vs.... Nvidia!

 

[Grim5]

Pointless^


Nvidia vs.... Nvidia!

Nvidia vs Nvidia

https://twitter.com/i/web/status/1667039238825582592

 

[Lightnix]

Nvidia vs Nvidia

https://twitter.com/i/web/status/1667039238825582592

Wonder what the 1% low averages of e.g. the 4060 ti and 3070 would look like if you forced all the textures to be the same as on higher VRAM cards.