Friday, February 21st 2025

AMD Radeon RX 9070 XT is a 304 W TBP Card, Regular RX 9070 Comes with 220 W Configuration

According to a well-known AMD hardware leaker, Hoang Anh Phu, AMD held a brief press conference where it confirmed that the upcoming Radeon RX 9070 XT and Radeon RX 9070 will carry a 304 Watt and 220 Watt total board power (TBP), respectively. While the post, originally on X is deleted, VideoCardz managed to read the information. AMD's TBP rating is similar to NVIDIA's total graphics power (TGP) metric, which measures both the chip and the memory and other components that the graphics card could contain under full load. So the TBP, and hence TGP, metrics are basically a rough outline of how much power the GPU will draw under full load.

AMD's upcoming Radeon RX 9070 XT and RX 9070 non-XT variants will consume 304 and 220 Watts, respectively, meaning that RDNA 4 IP will be relatively efficient. Interestingly, AMD settled on a 304-watt number instead of rounding it to 305, which usually happens. For reminder, the RX 9070 XT features 4,096 cores at 2.97 GHz boost clock, while the RX 9070 has 3,584 cores at 2.52 GHz. Both cards use a Navi 48 SKU, with 16 GB GDDR6 memory on a 256-bit bus running at 20 Gbps, achieving 640 GB/s bandwidth. Both utilize PCIe 5.0×16 and are rumored to be released on March 6, following their January announcement.
Source: VideoCardz
Add your own comment

64 Comments on AMD Radeon RX 9070 XT is a 304 W TBP Card, Regular RX 9070 Comes with 220 W Configuration

#1
jesdals
Show us some benchmarks already :)
Posted on Reply
#2
Caring1
Half the power of a 5090, I hope it performs well.
Posted on Reply
#3
TheGeekn°72
304 seems weirdly specific, like, they could have just said 300 or 305 and we'd have read the delta as margin of error or something, not sure why they felt the need to give out such a precise number...

besides that, I also saw the news about XFX's 9070XT magnetic air and it's looking real fine to me ! can't wait to snag a white one for my build !
Posted on Reply
#4
Daven
At the same power and fab node on a single monolithic die as the 4080S, the 9070XT better be the same performance. The 4080S has been on the market for over a year so AMD has had plenty of time to know it needs to be this fast. If the performance is there at half the price, it’s a gamer’s dream. I’m prepared to be disappointed on both fronts.
Posted on Reply
#6
mb194dc
jesdalsShow us some benchmarks already :)
64CU and 256bit memory bus, don't hold your breath too long...
Posted on Reply
#8
TheGeekn°72
mb194dc64CU and 256bit memory bus, don't hold your breath too long...
they're back to monolithic, used higher bandwidth VRAM modules and buffed up the CUs, as long as it gets perfs in the 7900XT-XTX gap for a decent enough price, I find that acceptable, no need for 4090 performance as long as it satisfies upper mid/high gaming reqs since it's what it's made for :)
Posted on Reply
#9
Easy Rhino
Linux Advocate
220 watts and 304 watts seems like a very large range between an non-XT and XT card...
Posted on Reply
#10
Vya Domus
DavenAt the same power and fab node on a single monolithic die as the 4080S, the 9070XT better be the same performance.
The 9070XT will for sure use a smaller die, you can't expect the same performance.
Posted on Reply
#11
TheGeekn°72
Vya DomusThe 9070XT will for sure use a smaller die, you can't expect the same performance.
RDNA4 and Blackwell are both 4nm
Posted on Reply
#12
Sound_Card
I would love the 9070 at 200w, but not at these market prices.
Posted on Reply
#14
jesdals
Hope that AMD release a lot of cards this surge of GPUs is not great for consumers
Posted on Reply
#15
Chrispy_
What matters at this point is pricing and availability.

Getting hold of an MSRP 5070Ti yesterday seemed like a lot of effort and a lot of luck, but we know that retailers have had 9070 series cards in stock for 6+ weeks at this point - so hopefully they won't be scalped the same way Nvidia's "$749" 5070Ti was.

I'm hoping for a $649 price on the stock-clocked XT. That's higher than the $500 price point AMD said they were targeting, and still a disappointment - but with the 5070 Ti currently going for $900, I think $649 would be an appealing alternative, provided it's genuinely at the 4080-tier raster performance and 4070Ti-tier RT performance.

I'm not so worried about the 304W TDP if the vanilla card uses 220W - it just means that the default clocks/voltages are being pushed far too hard for the XT and a bit of light undervolting and perhaps limiting the clocks to 2950MHz instead of >3.1GHz will get me 97% of the performance for a 20-30% power reduction.
Posted on Reply
#16
Vya Domus
DavenThe leaked die size of the 9070XT is 390mm^2. The die size of the 4080S is 380mm^2. The 9070XT is the same or slightly bigger than the 4080S.
I can just tell by looking at it that it's not 390mm^2, Navi 32 is 346mm^2 in total and it's not monolithic with a squarish aspect ratio and looks bigger. We'll see.
Posted on Reply
#17
Daven
Vya DomusI can just tell by looking at it that it's not 390mm^2, Navi 32 is 346mm^2 in total and it's not monolithic with a squarish aspect ratio and looks bigger. We'll see.
The estimated RDNA4 die size is from an RDNA4 die shown by AMD. Don't forget that AMD is greatly increasing RT performance. That probably requires more transistors. As I said before, I am prepared to be disappointed but RDNA4 is the same die size, monolithic design, power and process node as the 4080S. It should be close to the same performance if AMD has any skill at all.
Posted on Reply
#18
Darmok N Jalad
I know it's early, but, based on those 9070 specs, there's potential for a 9060 XT that could be a really interesting card. 12GB with ~3000 shaders and a sub-200W TDP, perhaps?
Posted on Reply
#19
Vya Domus
DavenThat probably requires more transistors.
Can't possibly be that much more, if it's a bigger chip than lets say Navi 32 then it's because it probably has more cache. It doesn't matter as the shader count itself says it probably wont have the same performance.
Posted on Reply
#20
alwayssts
jesdalsShow us some benchmarks already :)
Accurate.

I'm pretty f'in toasted on talking about it until we know everything about it. (For me at least) it's fun to speculate and try to understand what they may do with the product, but this has been excessive.

I mean, this is our hobby and it's what we (and I) do...but sheesh. This prolonged escapade has been tiring for everyone, I think (and yes I do admit to my part in contributing to that).
TheGeekn°72they're back to monolithic, used higher bandwidth VRAM modules and buffed up the CUs, as long as it gets perfs in the 7900XT-XTX gap for a decent enough price, I find that acceptable, no need for 4090 performance as long as it satisfies upper mid/high gaming reqs since it's what it's made for :)
VRAM isn't faster though...that's the whole (potential) problem. If you think these are faster will likely depend on how you measure performance. RT buffed probably ~30% (per cu).
...and then you have to go by things like actual memory bandwidth and/or if you overclock. The actual flop/buffer if you overclock 7900xt will exceed these cards. If you don't,

Well, then 12288*2631 (7900xtx)/ 8192*2970 = 1.33x. There's a good chance *in not compute/buffer/bw-limited scenarios* it, or higher clocked models could match or exceed it in RT.
This is about the difference between nVIDIA and Navi3 (performance per unit per clock) and odds are by doubling TMUs (or whatever TAUs they added) likley could/will make up the difference.
Chrispy_What matters at this point is pricing and availability.

Getting hold of an MSRP 5070Ti yesterday seemed like a lot of effort and a lot of luck, but we know that retailers have had 9070 series cards in stock for 6+ weeks at this point - so hopefully they won't be scalped the same way Nvidia's "$749" 5070Ti was.

I'm hoping for a $649 price on the stock-clocked XT. That's higher than the $500 price point AMD said they were targeting, and still a disappointment - but with the 5070 Ti currently going for $900, I think $649 would be an appealing alternative, provided it's genuinely at the 4080-tier raster performance and 4070Ti-tier RT performance.

I'm not so worried about the 304W TDP if the vanilla card uses 220W - it just means that the default clocks/voltages are being pushed far too hard for the XT and a bit of light undervolting and perhaps limiting the clocks to 2950MHz instead of >3.1GHz will get me 97% of the performance for a 20-30% power reduction.
I'm still hoping AMD is trying to surprise us with the prices we initially expected.
I still think everything points to it *used* to be ~400/480 (many accounts of this from CES plus leaked bulgarian prices converted), and we saw that one (Gigabyte?) model listed for $530. That makes sense.

Listen, if I'm wrong I'm wrong and that's fine...It's not cope, it's a very fair/realistic opinion...but they could do it, and they should do it. If they changed it, they changed it...but then it's just a worse-to-bad deal!

Again, I'm as tired of this discussion as everyone...I truly am.
Vya DomusCan't possibly be that much more, if it's a bigger chip than lets say Navi 32 then it's because it probably has more cache. It doesn't matter as the shader count itself says it probably wont have the same performance.
Cache is possible, but again it also could be related to both the increased texture capability (for ray-tracing) we know to be true (gpu-z) if not allowing for much higher clocks. Again, the later long-speculated.

Again, look at 5070's die size. It is also strangely large for it's configuration (similar to 4070 series but 80% of units). Does it clock 25% higher? I don't know. Maybe! (Probably, actually).
This is why people should not be surprised by 3400-3500 (or even potentially greater) clockspeeds. They *could* happen. The process is built for it. Do I *know* they'll do this? No.
TheGeekn°72304 seems weirdly specific, like, they could have just said 300 or 305 and we'd have read the delta as margin of error or something, not sure why they felt the need to give out such a precise number...

besides that, I also saw the news about XFX's 9070XT magnetic air and it's looking real fine to me ! can't wait to snag a white one for my build !
304 * 15%+ PL = 350W

Like i've speculated...pretty sure they're binning and power/clock locking these chips so they fit in very particular categories. Will wait for W1zard's analysis to confirm.

I'm very curious the clock potential of the chip. If the cache isn't increased, and the VRAM isn't increased, but it clocks well then this (XT) being the top product makes no sense. We shall see.

All I know is, don't (necessarily)trust Frank. That's his job.
Posted on Reply
#21
Daven
Vya DomusCan't possibly be that much more, if it's a bigger chip than lets say Navi 32 then it's because it probably has more cache. It doesn't matter as the shader count itself says it probably wont have the same performance.
There is also more AI compute for FSR4 and better media encoding quality. As you said there could be more cache. But I'm also learning a thing or two about targeted transistor density to achieve higher or lower clocks. Like the opposite of Zen 4c and 5c, AMD doesn't have to space the transistors as close as a process node allows. More spacing between transistors allows for higher clock speeds and we are hearing about boost speeds as high as 3100 MHz (maybe even higher).
Posted on Reply
#22
Nostras
Easy Rhino220 watts and 304 watts seems like a very large range between an non-XT and XT card...
This is actually somewhat concerning to me. This probably means that the card starts hitting diminishing returns at the 200-250W range and AMD is only ramming +300W through the XT model to hit a certain performance milestone.
Posted on Reply
#23
INSTG8R
Vanguard Beta Tester
Easy Rhino220 watts and 304 watts seems like a very large range between an non-XT and XT card...
Yeah that’s a seriously big power gap that stood out to me too
Posted on Reply
#24
Darmok N Jalad
INSTG8RYeah that’s a seriously big power gap that stood out to me too
Well, the XT has 14% more shaders and runs at 18% higher clocks. A 38% increase in TBP isn't too far out of line, IMO, especially when you consider the non-XT is probably running the harvested dies at a conservative speed, and the XT is running the best dies somewhere on the right side of the performance/efficiency curve intersection.
Posted on Reply
#25
Daven
INSTG8RYeah that’s a seriously big power gap that stood out to me too
The 9070 (56 CUs) is 220W. The 9070XT (64 CUs) is 300W. Difference 80W.

The 4070S (56 CUDA cores) is 220W. The 4070TiS (66 CUDA cores) is 285W. Difference 65W.

I don't think the gap is different enough compared to other examples to warrant any concern.
Posted on Reply
Add your own comment
Feb 22nd, 2025 00:16 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts