ATI Radeon HD 5970 vs RTX PRO 4000 Blackwell
We compared two Desktop platform GPUs: 1024MB VRAM ATI Radeon HD 5970 and 24GB VRAM RTX PRO 4000 Blackwell to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
RTX PRO 4000 Blackwell 's Advantages
Released 15 years and 4 months late
Boost Clock2617MHz
More VRAM (24GB vs 1024GB)
Larger VRAM bandwidth (672.0GB/s vs 128.0GB/s)
7360 additional rendering cores
Lower TDP (140W vs 294W)
Score
Benchmark
FP32 (float)
ATI Radeon HD 5970
2320
RTX PRO 4000 Blackwell
+1921%
46900
Graphics Card
Nov 2009
Release Date
Mar 2025
Evergreen
Generation
Blackwell PRO W
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1590 MHz
-
Boost Clock
2617 MHz
1000 MHz
Memory Clock
1750 MHz
Memory
1024MB
Memory Size
24GB
GDDR5
Memory Type
GDDR7
256bit
Memory Bus
192bit
128.0GB/s
Bandwidth
672.0GB/s
Render Config
20
Compute Units
-
-
SM Count
70
1600
Shading Units
8960
80
TMUs
280
32
ROPs
96
-
Tensor Cores
280
-
RT Cores
70
8 KB (per CU)
L1 Cache
128 KB (per SM)
512 KB
L2 Cache
48 MB
Theoretical Performance
23.20 GPixel/s
Pixel Rate
251.2 GPixel/s
58.00 GTexel/s
Texture Rate
732.8 GTexel/s
-
FP16 (half)
46.90 TFLOPS
2.320 TFLOPS
FP32 (float)
46.90 TFLOPS
464.0 GFLOPS
FP64 (double)
732.8 GFLOPS
Board Design
294W
TDP
140W
600 W
Suggested PSU
300 W
2x DVI
1x mini-DisplayPort 1.1
Outputs
4x DisplayPort 2.1b
1x 6-pin + 1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
Hemlock
GPU Name
GB203
Hemlock XT
(215-0735075)
GPU Variant
-
TeraScale 2
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
40 nm
Process Size
5 nm
2.154 billion
Transistors
45.6 billion
334 mm²
Die Size
378 mm²
Graphics Features
11.2 (11_0)
DirectX
12 Ultimate (12_2)
4.4
OpenGL
4.6
1.2
OpenCL
3.0
N/A
Vulkan
1.4
-
CUDA
10.1
5.0
Shader Model
6.8
