NVIDIA GeForce RTX 5090 vs AMD Radeon Pro 580
GPU · Specs Compare
Graphics Card
Release Date
Jan 2025
Jun 2017
Generation
GeForce 50
Radeon Pro Mac
Type
Desktop
Mobile
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
2017 MHz
1100 MHz
Boost Clock
2407 MHz
1200 MHz
Memory Clock
1750 MHz
1695 MHz
Memory
Memory Size
32GB
8GB
Memory Type
GDDR7
GDDR5
Memory Bus
512bit
256bit
Bandwidth
1.79TB/s
217.0GB/s
Render Config
SM Count
170
—
Shading Units
21760
2304
TMUs
680
144
ROPs
176
32
Tensor Cores
680
—
RT Cores
170
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
96 MB
2 MB
Compute Units
—
36
Theoretical Performance
Pixel Rate
423.6 GPixel/s
38.40 GPixel/s
Texture Rate
1636.8 GTexel/s
172.8 GTexel/s
FP16 (half)
104.8 TFLOPS
5.530 TFLOPS
FP32 (float)
104.8 TFLOPS
5.530 TFLOPS
FP64 (double)
1.637 TFLOPS
345.6 GFLOPS
Graphics Processor
GPU Name
GB202
Ellesmere
GPU Variant
GB202-300-A1
Ellesmere XTA(216-0886220)
Architecture
Blackwell 2.0
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
5 nm
14 nm
Transistors
92.2 billion
5.7 billion
Die Size
750 mm²
232 mm²
Board Design
TDP
575W
185W
Suggested PSU
950 W
—
Outputs
1x HDMI 2.1b3x DisplayPort 2.1b
No outputs
Power Connectors
1x 16-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.4
1.2
CUDA
12.0
—
Shader Model
6.9
6.4
Benchmark
3DMark Time Spy
46,923
3,791
3DMark Time Spy Extreme
25,766
1,684
3DMark Speed Way
14,614
—
Blender
14,945
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.