NVIDIA GeForce RTX 5090 D vs AMD Radeon HD 6870
GPU · Specs Compare
Graphics Card
Release Date
Jan 2025
Oct 2010
Generation
GeForce 50
Northern Islands
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 2.0 x16
Clock Speeds
Base Clock
2017 MHz
—
Boost Clock
2407 MHz
—
Memory Clock
1750 MHz
1050 MHz
Memory
Memory Size
32GB
1024MB
Memory Type
GDDR7
GDDR5
Memory Bus
512bit
256bit
Bandwidth
1.79TB/s
134.4GB/s
Render Config
SM Count
170
—
Shading Units
21760
1120
TMUs
680
56
ROPs
176
32
Tensor Cores
680
—
RT Cores
170
—
L1 Cache
128 KB (per SM)
8 KB (per CU)
L2 Cache
96 MB
512 KB
Compute Units
—
14
Theoretical Performance
Pixel Rate
423.6 GPixel/s
28.80 GPixel/s
Texture Rate
1636.8 GTexel/s
50.40 GTexel/s
FP16 (half)
104.8 TFLOPS
—
FP32 (float)
104.8 TFLOPS
2.016 TFLOPS
FP64 (double)
1.637 TFLOPS
—
Graphics Processor
GPU Name
GB202
Barts
GPU Variant
GB202-250-A1
Barts XT(215-0798000)
Architecture
Blackwell 2.0
TeraScale 2
Foundry
TSMC
TSMC
Process Size
5 nm
40 nm
Transistors
92.2 billion
1.7 billion
Die Size
750 mm²
255 mm²
Board Design
TDP
575W
151W
Suggested PSU
950 W
450 W
Outputs
1x HDMI 2.1b3x DisplayPort 2.1b
2x DVI1x HDMI 1.3a2x mini-DisplayPort 1.1
Power Connectors
1x 16-pin
2x 6-pin
Graphics Features
DirectX
12 Ultimate (12_2)
11.2 (11_0)
OpenGL
4.6
4.4
OpenCL
3.0
1.2
Vulkan
1.4
N/A
CUDA
12.0
—
Shader Model
6.8
5.0
Benchmark
3DMark Time Spy
48,052
—
3DMark Time Spy Extreme
25,999
—
3DMark Speed Way
14,790
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.