NVIDIA RTX PRO 4000 Blackwell vs AMD Radeon RX 580 OEM
GPU · Specs Compare
Graphics Card
Release Date
Mar 2025
Jun 2016
Generation
Blackwell PRO W
Polaris
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1230 MHz
1120 MHz
Boost Clock
2055 MHz
1266 MHz
Memory Clock
1750 MHz
2000 MHz
Memory
Memory Size
24GB
8GB
Memory Type
GDDR7
GDDR5
Memory Bus
192bit
256bit
Bandwidth
672.0GB/s
256.0GB/s
Render Config
SM Count
70
—
Shading Units
8960
2304
TMUs
280
144
ROPs
96
32
Tensor Cores
280
—
RT Cores
70
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
48 MB
2 MB
Compute Units
—
36
Theoretical Performance
Pixel Rate
197.3 GPixel/s
40.51 GPixel/s
Texture Rate
575.4 GTexel/s
182.3 GTexel/s
FP16 (half)
36.83 TFLOPS
5.834 TFLOPS
FP32 (float)
36.83 TFLOPS
5.834 TFLOPS
FP64 (double)
575.4 GFLOPS
364.6 GFLOPS
Graphics Processor
GPU Name
GB203
Ellesmere
Architecture
Blackwell 2.0
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
5 nm
14 nm
Transistors
45.6 billion
5.7 billion
Die Size
378 mm²
232 mm²
GPU Variant
—
Polaris 10 XT(215-0876184)
Board Design
TDP
140W
150W
Suggested PSU
300 W
450 W
Outputs
4x DisplayPort 2.1b
1x HDMI 2.0b3x DisplayPort 1.4a
Power Connectors
1x 16-pin
1x 6-pin
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
6.8
6.4
▲ Specs Compare
Data sourced from official specifications and benchmark tests.