NVIDIA GeForce RTX 4090 Max-Q vs AMD Radeon HD 6870 1600SP Edition

GPU · Specs Compare

Products
GPU NVIDIA GeForce RTX 4090 Max-Q NVIDIA · 2023-01
Graphics Card
Release Date
Jan 2023
Jan 2013
Generation
GeForce 40 Mobile
Northern Islands
Type
Mobile
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Clock Speeds
Base Clock
930 MHz
—
Boost Clock
1455 MHz
—
Memory Clock
1750 MHz
1050 MHz
Memory
Memory Size
16GB
1024MB
Memory Type
GDDR6
GDDR5
Memory Bus
256bit
256bit
Bandwidth
448.0GB/s
134.4GB/s
Render Config
SM Count
76
—
Shading Units
9728
1600
TMUs
304
80
ROPs
112
32
Tensor Cores
304
—
RT Cores
76
—
L1 Cache
128 KB (per SM)
8 KB (per CU)
L2 Cache
64 MB
512 KB
Compute Units
—
20
Theoretical Performance
Pixel Rate
163.0 GPixel/s
27.20 GPixel/s
Texture Rate
442.3 GTexel/s
68.00 GTexel/s
FP16 (half)
28.31 TFLOPS
—
FP32 (float)
28.31 TFLOPS
2.720 TFLOPS
FP64 (double)
442.3 GFLOPS
544.0 GFLOPS
Graphics Processor
GPU Name
AD103
Cypress
GPU Variant
GN21-X11
Cypress XT(215-0735033)
Architecture
Ada Lovelace
TeraScale 2
Foundry
TSMC
TSMC
Process Size
4 nm
40 nm
Transistors
45.9 billion
2.154 billion
Die Size
379 mm²
334 mm²
Board Design
TDP
80W
175W
Outputs
Portable Device Dependent
2x DVI1x HDMI 1.3a2x mini-DisplayPort 1.1
Power Connectors
None
2x 6-pin
Suggested PSU
—
450 W
Graphics Features
DirectX
12 Ultimate (12_2)
11.2 (11_0)
OpenGL
4.6
4.4
OpenCL
3.0
1.2
Vulkan
1.3
N/A
CUDA
8.9
—
Shader Model
6.7
5.0
▲ Specs Compare Data sourced from official specifications and benchmark tests.