Architecture
NVIDIA Ampere 8nm
Most Powerful Variant
GA104-300
Cores : TMUs : ROPs
5888 : 184 : 96
Typical Memory Size
8192 MB
Typical Memory Bus
256 -bit
GA104 GPU
Overview
Manufacturer
NVIDIA
Release Date
October 29th, 2020
Graphics Processing Unit
Architecture
Ampere
Fabrication Process
8 nm
Die Size
392 mm2
Transistors Count
17.4B
Tensor Cores
184
RT Cores
46
CUDAs
5888
TMUs
184
ROPs
96
Clocks
Base Clock
1500 MHz
Memory Configuration
Memory Size
8192 MB
Memory Type
GDDR6
Memory Bus Width
256-bit
Memory Bandwidth
448.0 GB/s
Performance
Pixel Fillrate
165.6 GPixels/s
Texture Fillrate
317.4 GTexel/s
SPFP Performance
20.3 TFLOPS
Performance per W
92.3 GFLOPS/W
Performance per mm2
51.8 GFLOPS/mm2
Physical
Interface
PCI-Express 4.0 x16
Typical Thermal Design Power
220 W
SLI Support
Unsupported
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
2.1
| Model | GPU Model | Unified Cores | Boost Clock | Memory Clock | Memory Config. | |
|---|---|---|---|---|---|---|
 | NVIDIA GeForce RTX 3080 Mobile | GN20-E7 | TBC | TBC | TBC | TBC |
 | NVIDIA GeForce RTX 3070 | GA104-300 | ||||
 | NVIDIA GeForce RTX 3070 Mobile | GN20-E5 | TBC | TBC | TBC | TBC |
| | NVIDIA GeForce RTX 3060 Ti | GA104-200 | ||||
| | NVIDIA GeForce RTX 3070 SUPER | GA104 | TBC | TBC | TBC | TBC |
| | NVIDIA GeForce RTX 3060 SUPER | GA104-200 | TBC | TBC | TBC | TBC |