NVIDIA unveiled their Ada Lovelace architecture last month while announcing the RTX 4090 along with the 4080 12/16GB. AMD is aiming at the 3rd of November to showcase their RDNA3 GPUs. Today, as pointed out by momomo_us the Enermax PSU calculator has listed the alleged power consumption numbers for these GPUs.
Ada Lovelace
Across all 4 hypothetical test systems, we have the i9-12900KF paired with 2x32GB of DDR5 memory. Do note that we already know the power consumption of the RTX 4090 and the 4080 16GB/12GB. This makes calculating the TDP of the 4070 and the 4060 much easier.
Since, the RTX 4090 has a TDP of 450W, the rest of the system consumes about ~400W.
- RTX 4090 -> 850W – 400W= 450W
- RTX 4080 16GB – > 720W – 400W = 320W
- RTX 4070 -> 680W – 400W = 280W
- RTX 4060 -> 600W – 400W = 200W
These numbers are either a rough estimate or official figures. All in all, the TDP increase from generation to generation is quite visible.
| 60 Series (Watts) | TDP Increase Gen On Gen | 70 Series (Watts) | TDP Increase Gen On Gen | |
| RTX 4000 | 200 | 17.65% | 280 | 27.27% |
| RTX 3000 | 170 | 6.25% | 220 | 25.71% |
| RTX 2000 | 160 | 33.33% | 175 | 16.67% |
RDNA3
Moving over to AMD, we see almost similar numbers as compared to NVIDIA. The power difference again remains at 400W.
- RX 7950 XT -> 820- 400W= 420W
- RX 7900 XT– > 730W – 400W = 330W
- RX 7800 XT-> 700W – 400W = 300W
- RX 7700 XT-> 600W – 400W = 200W
This listing confirms the existence of an RX 7950 XT, which will probably have 2 variants. One with the full fledged Navi31 GPU and the other with X3D cache. Maybe AMD will combine the best of both worlds into a single GPU. On a generation-generation comparison, Navi32/Navi33 appear to be much more efficient than Navi22/23. Although, Navi31 may just be AMD pushing the limits to beat the RTX 4090/4090 Ti.
| X950 Series (Watts) | X950 Series % Gen on Gen | X900 Series (Watts) | X900 Series % Gen on Gen | X800 Series (Watts) | X800 Series % Gen on Gen | X700 Series (Watts) | X700 Series % Gen on Gen | X600 Series (Watts) | X600 Series % Gen on Gen | |
| RX 7000 | 420 | 25.37% | 330 | 10.00% | 300 | 0.00% | 200 | -13.04% | – | – |
| RX 6000 | 335 | – | 300 | – | 300 | – | 230 | 2.22% | 160 | 6.67% |
| RX 5000 | – | – | – | – | – | – | 225 | – | 150 | – |
RDNA3 & Ada Lovelace Lineup
We’ve compiled all the information and speculations regarding RDNA3 & Lovelace so far into 2 comprehensive charts.
| SKU | Chip | CU | FP32 | Max Clock | Cache | Memory Bus | VRAM | Memroy Spec | Speed (Gbps) | TDP | ||||
| RX 7970XT3D | Navi31 | 96 | 12288 | 3.2 GHz | 192MB? | 384-bit | 24GB | GDDR6 | 24 | 450W | ||||
| RX 7950XT | Navi31 | 92? | 10752 | 3.1 GHz | 96MB | 384-bit | 24GB | GDDR6 | 24 | 400W | ||||
| RX 7900XT | Navi31 | 84? | 8960 | 3.0 GHz | 80MB | 320-bit | 20GB | GDDR6 | 20 | 340W | ||||
| RX 7800XT | Navi32 | 60 | 7680 | 3.4 GHz | 64MB | 256-bit | 16GB | GDDR6 | 18 | 285W | ||||
| RX 7800 | Navi32 | 56 | 7168 | 3.3 GHz | 48MB? | 256-bit | 16GB | GDDR6 | 18 | 250W | ||||
| RX 7700XT | Navi32 | 48 | 6144 | 3.2 GHz | 48MB? | 192-bit | 12GB | GDDR6 | 18 | 200W | ||||
| RX 7700 | Navi32? | 36? | 5120? | 3.1GHz | 40MB? | 160-bit? | 10GB? | GDDR6 | 18 | 175W | ||||
| RX 7600XT | Navi33 | 32 | 4096 | 3.2 GHz | 32MB | 128-bit | 8GB | GDDR6 | 18 | 150W | ||||
| RX 7600 | Navi33 | 28 | 3584 | 3.1 GHZ? | 32MB? | 128-bit | 8GB | GDDR6 | 18 | 130W | ||||
| SKU | Chip | FP32/CUDA | Max Clock | Cache | Memory Bus | VRAM | Memory Spec | Speed (Gbps) | TDP | |||
| RTX 4000 Titan? | AD102-450 | 18176 | 3.0GHz+? | 96MB? | 384/382-bit | 48GB | GDDR6X | 24 | ~800W | |||
| RTX 4090 Ti | AD102-350 | 18432 | 3.0 GHz? | 96MB | 382-bit | 24GB | GDDR6X | 24 | 600W? | |||
| RTX 4090 | AD102-300-A1 | 16384 | 2.52GHz | 96MB | 384-bit | 24GB | GDDR6X | 21 | 450W+ (TGP) / 660W (Max TGP) | |||
| RTX 4080 Ti | AD102 | 14848? | 2.7 GHz? | 80MB? | 320-bit | 20GB | GDDR6X | 23 | 420W | |||
| RTX 4080 (Variant 1) | AD103-300-A1 | 9728 | 2.505GHz | 64MB | 256-bit | 16GB | GDDR6X | 22.5 | 320W(TGP)/ 516W (Max TGP) | |||
| RTX 4080 (Variant 2) | AD104-400-A1 | 7680 | 2.61GHz | 48MB | 192-bit | 12GB | GDDR6X | 21 | 285W (TGP) /366W (Max TGP) | |||
| RTX 4070 Ti | AD104-300? | 7680 | 3.0GHz? | ? | 192-bit | 12GB | GDDR6X | 21 | 300W? | |||
| RTX 4070 | AD104-275? | 7168 | ? | ? | 160-bit | 10GB | GDDR6X | 21 | 250W | |||
Featured image background via Freepik
The post Power Consumption Figures For AMD’s RDNA3 & NVIDIA’s Lovelace GPUs Surface appeared first on Appuals.com.
0 Commentaires