Architecture
NVIDIA Ada 4nm
Most Powerful Variant
AD102
Cores : TMUs : ROPs
18176 : 568 : 192
Typical Memory Size
49152 MB
Typical Memory Bus
384 -bit
AD102 GPU
Overview
Manufacturer
NVIDIA
Release Date
January 17th, 2023
Graphics Processing Unit
Architecture
Ada
Fabrication Process
4 nm
Die Size
608 mm2
Transistors Count
76.3B
Tensor Cores
568
RT Cores
142
CUDAs
18176
TMUs
568
ROPs
192
Clocks
Boost Clock
2506 MHz
Memory Configuration
Memory Size
49152 MB
Memory Type
GDDR6
Memory Bus Width
384-bit
Memory Bandwidth
960.0 GB/s
Performance
Pixel Fillrate
481.2 GPixels/s
Texture Fillrate
1.4 TTexel/s
SPFP Performance
91.1 TFLOPS
Performance per W
303.7 GFLOPS/W
Performance per mm2
149.8 GFLOPS/mm2
Physical
Interface
PCI-Express 4.0 x16
Typical Thermal Design Power
300 W
SLI Support
Unsupported
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
3.0
| Model | GPU Model | Unified Cores | Boost Clock | Memory Clock | Memory Config. | |
|---|---|---|---|---|---|---|
 | NVIDIA TITAN RTX ADA | AD102 | TBC | TBC | TBC | TBC |
 | NVIDIA RTX 6000 ADA | AD102 | ||||
 | NVIDIA L40 | AD102 | TBC | TBC | TBC | TBC |
| | NVIDIA GeForce RTX 4090 Ti | AD102 | TBC | TBC | TBC | TBC |
 | NVIDIA GeForce RTX 4090 | AD102-300 |
