Architecture
NVIDIA Ada 4nm
Most Powerful Variant
AD107-400
Cores : TMUs : ROPs
3072 : 96 : 64
Typical Memory Size
8192 MB
Typical Memory Bus
128 -bit
AD107 GPU
Overview
Manufacturer
NVIDIA
Release Date
June 29th, 2023
Graphics Processing Unit
Architecture
Ada
Fabrication Process
4 nm
Die Size
146 mm2
Tensor Cores
96
RT Cores
28
CUDAs
3072
TMUs
96
ROPs
64
Clocks
Base Clock
1830 MHz
Memory Configuration
Memory Size
8192 MB
Memory Type
GDDR6
Memory Bus Width
128-bit
Memory Bandwidth
272.0 GB/s
Performance
Pixel Fillrate
157.4 GPixels/s
Texture Fillrate
236.2 GTexel/s
SPFP Performance
15.1 TFLOPS
Performance per W
131.4 GFLOPS/W
Performance per mm2
103.5 GFLOPS/mm2
Physical
Interface
PCI-Express 4.0 x8
Typical Thermal Design Power
115 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 GeForce RTX 4060 Laptop GPU | X21-X4 | ||||
 | NVIDIA GeForce RTX 4060 | AD107-400 | ||||
| | NVIDIA RTX A2000 ADA Laptop GPU | AD107 | ||||
 | NVIDIA RTX 2000 ADA | AD107 | ||||
| | NVIDIA GeForce RTX 4050 Laptop GPU | X21-X2 | ||||
| | NVIDIA RTX A1000 ADA Laptop GPU | AD107 | ||||
| | NVIDIA RTX A500 ADA Laptop GPU | AD107 |
