NVIDIA RTX 6000D vs AMD Radeon R9 M470X

GPU · Specs Compare

Products
GPU NVIDIA RTX 6000D NVIDIA · 2025-07
GPU AMD Radeon R9 M470X AMD · 2016-05
Graphics Card
Release Date
Jul 2025
May 2016
Generation
Blackwell PRO W
Gem System
Type
Desktop
Mobile
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1992 MHz
1000 MHz
Boost Clock
2430 MHz
1100 MHz
Memory Clock
1560 MHz
1200 MHz
Memory
Memory Size
84GB
4GB
Memory Type
GDDR7
GDDR5
Memory Bus
448bit
128bit
Bandwidth
1.40TB/s
76.80GB/s
Render Config
SM Count
156
—
Shading Units
19968
896
TMUs
624
56
ROPs
192
16
Tensor Cores
624
—
RT Cores
156
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
128 MB
256 KB
Compute Units
—
14
Theoretical Performance
Pixel Rate
466.6 GPixel/s
17.60 GPixel/s
Texture Rate
1516.3 GTexel/s
61.60 GTexel/s
FP16 (half)
97.04 TFLOPS
—
FP32 (float)
97.04 TFLOPS
1.971 TFLOPS
FP64 (double)
1.516 TFLOPS
123.2 GFLOPS
Graphics Processor
GPU Name
GB202
Emerald
Architecture
Blackwell 2.0
GCN 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
28 nm
Transistors
92.2 billion
2.08 billion
Die Size
750 mm²
160 mm²
GPU Variant
—
Emerald XT
Board Design
TDP
600W
Unknown
Suggested PSU
1000 W
—
Outputs
4x DisplayPort 2.1b
Portable Device Dependent
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.4
1.2.170
CUDA
12.0
—
Shader Model
6.9
6.5
▲ Specs Compare Data sourced from official specifications and benchmark tests.