Home NVIDIA GeForce RTX 4080 Ti

NVIDIA GeForce RTX 4080 Ti

This is a GPU manufactured with TSMC 5nm process, based on Nvidia Ada Lovelace architecture. It features 76.3 billion transistors, 14080 CUDA cores and 20GB GDDR6X memory, with 80MB L2 cache, theoretical performance of 67.58TFLOPS, with total power consumption of 400W.

Graphics Card

[Report Issues]
Release Date
Unknown
Generation
GeForce 40
Type
Desktop
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
2100MHz
Boost Clock
2400MHz
Memory Clock
1325MHz

Memory

[Report Issues]
Memory Size
20GB
Memory Type
GDDR6X
Memory Bus
320bit
Bandwidth
848.0 GB/s

Render Config

[Report Issues]
SM Count
110
Shading Units
14080
TMUs
440
ROPs
144
Tensor Cores
440
RT Cores
110
L1 Cache
128 KB (per SM)
L2 Cache
80MB

Theoretical Performance

[Report Issues]
Pixel Rate
345.6 GPixel/s
Texture Rate
1056 GTexel/s
FP16 (half)
67.58 TFLOPS
FP32 (float)
67.58 TFLOPS
FP64 (double)
1056 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
AD102
GPU Variant
AD102-225-A1
Architecture
Ada Lovelace
Foundry
TSMC
Process Size
5 nm
Transistors
76,300 million
Die Size
609mm²

Board Design

[Report Issues]
TDP
400W
Suggested PSU
800W
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
Power Connectors
1x 16-pin

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.9
Shader Model
6.7

Rankings

[Report Issues]
FP32 (float)
73.54 TFLOPS
73.54 TFLOPS
69.27 TFLOPS
67.58 TFLOPS
H200 SXM 141 GB HBM3e
67 TFLOPS
NVIDIA H100 SXM5 80 GB HBM3
66.91 TFLOPS
66.91 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy