Architecture
NVIDIA Turing 12nm (RTX)
Most Powerful Variant
TU104-875
Cores : TMUs : ROPs
3072 : 192 : 64
Typical Memory Size
16384 MB
Typical Memory Bus
256 -bit
TU104 GPU
Overview
Manufacturer
NVIDIA
Release Date
December 31st, 2018
Graphics Processing Unit
Architecture
Turing (RTX)
Fabrication Process
12 nm FinFET
Die Size
545 mm2
Transistors Count
13.6B
Tensor Cores
384
RT Cores
48
CUDAs
3072
TMUs
192
ROPs
64
Clocks
Base Clock
1620 MHz
Memory Configuration
Memory Size
16384 MB
Memory Type
GDDR6
Memory Bus Width
256-bit
Memory Bandwidth
448.0 GB/s
Performance
Pixel Fillrate
116.2 GPixels/s
Texture Fillrate
348.5 GTexel/s
SPFP Performance
11.2 TFLOPS
Performance per W
42.1 GFLOPS/W
Performance per mm2
20.5 GFLOPS/mm2
Physical
Interface
PCI-Express 3.0 x16
Typical Thermal Design Power
265 W
SLI Support
2-way
API Support
DirectX
12.2
Vulkan
1.0
OpenGL
4.5
OpenCL
3.0
| Model | GPU Model | Unified Cores | Boost Clock | Memory Clock | Memory Config. | |
|---|---|---|---|---|---|---|
 | NVIDIA Quadro RTX 5000 | TU104-875 | ||||
 | NVIDIA Quadro RTX 5000 Mobile | N19E-Q5 | ||||
| | NVIDIA Quadro RTX 5000 Mobile Max-Q | N19E-Q5 | ||||
 | NVIDIA GeForce RTX 2080 SUPER | TU104-450 | ||||
| | NVIDIA GeForce RTX 2080 SUPER Mobile | N18E-G3R | ||||
| | NVIDIA GeForce RTX 2080 SUPER Mobile Max-Q | N18E-G3R | ||||
 | NVIDIA GeForce GTX 2080 Prototype | TU104-400/A | ||||
 | NVIDIA GeForce RTX 2080 | TU104-400/A | ||||
 | NVIDIA GeForce RTX 2080 Mobile | N18E-G3 | ||||
| | NVIDIA GeForce RTX 2080 Mobile Max-Q | N18E-G3 | ||||
 | NVIDIA Tesla T4 | TU104-895 | ||||
 | NVIDIA GeForce RTX 2070 SUPER | TU104-410 | ||||
| | NVIDIA GeForce RTX 2070 SUPER Mobile | N18E-G2R | ||||
| | NVIDIA Quadro RTX 4000 Mobile | N19E-Q3 | ||||
| | NVIDIA GeForce RTX 2070 SUPER Mobile Max-Q | N18E-G2R | ||||
| | NVIDIA Quadro RTX 4000 Mobile Max-Q | N19E-Q3 |
