AMD Radeon RX Vega M GH vs NVIDIA RTX PRO 6000 Blackwell

GPU · Specs Compare

Products
GPU AMD Radeon RX Vega M GH AMD · 2018-02
GPU NVIDIA RTX PRO 6000 Blackwell NVIDIA · 2025-03
Graphics Card
Release Date
Feb 2018
Mar 2025
Generation
Vega
Blackwell PRO W
Type
Mobile
Desktop
Bus Interface
IGP
PCIe 5.0 x16
Clock Speeds
Base Clock
1063 MHz
1590 MHz
Boost Clock
1190 MHz
2617 MHz
Memory Clock
800 MHz
1750 MHz
Memory
Memory Size
4GB
96GB
Memory Type
HBM2
GDDR7
Memory Bus
1024bit
512bit
Bandwidth
204.8GB/s
1.79TB/s
Render Config
Compute Units
24
—
Shading Units
1536
24064
TMUs
96
752
ROPs
64
192
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
128 MB
SM Count
—
188
Tensor Cores
—
752
RT Cores
—
188
Theoretical Performance
Pixel Rate
76.16 GPixel/s
502.5 GPixel/s
Texture Rate
114.2 GTexel/s
1968.0 GTexel/s
FP16 (half)
3.656 TFLOPS
126.0 TFLOPS
FP32 (float)
3.656 TFLOPS
126.0 TFLOPS
FP64 (double)
228.5 GFLOPS
1.968 TFLOPS
Graphics Processor
GPU Name
Polaris 22
GB202
GPU Variant
VegaM XT(C7398773)
—
Architecture
GCN 4.0
Blackwell 2.0
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
5 nm
Transistors
5 billion
92.2 billion
Die Size
208 mm²
750 mm²
Board Design
TDP
100W
600W
Outputs
No outputs
4x DisplayPort 2.1b
Suggested PSU
—
1000 W
Power Connectors
—
1x 16-pin
Graphics Features
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.2
1.4
Shader Model
6.4
6.9
CUDA
—
12.0
Benchmark
3DMark Time Spy
—
42,269
3DMark Time Spy Extreme
—
27,891
3DMark Speed Way
—
15,642
▲ Specs Compare Data sourced from official specifications and benchmark tests.