Home GPU Comparison NVIDIA T400 vs NVIDIA GeForce RTX 5090

NVIDIA T400 vs NVIDIA GeForce RTX 5090

We compared two Desktop platform GPUs: 2GB VRAM T400 and 28GB VRAM GeForce RTX 5090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA T400 's Advantages
Lower TDP (30W vs 500W)
NVIDIA GeForce RTX 5090 's Advantages
Released 3 years and 8 months late
Boost Clock has increased by 77% (2520MHz vs 1425MHz)
More VRAM (28GB vs 2GB)
Larger VRAM bandwidth (280.0GB/s vs 80.00GB/s)
20096 additional rendering cores

Score

Benchmark

FP32 (float)
T400
1.094 TFLOPS
GeForce RTX 5090 +9333%
103.2 TFLOPS
VS

Graphics Card

May 2021
Release Date
Jan 2025
Quadro
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16

Clock Speeds

420 MHz
Base Clock
2235 MHz
1425 MHz
Boost Clock
2520 MHz
1250 MHz
Memory Clock
2500 MHz

Memory

2GB
Memory Size
28GB
GDDR6
Memory Type
GDDR7
64bit
Memory Bus
448bit
80.00GB/s
Bandwidth
280.0GB/s

Render Config

6
SM Count
160
-
Compute Units
-
384
Shading Units
20480
24
TMUs
640
16
ROPs
192
-
Tensor Cores
640
-
RT Cores
160
64 KB (per SM)
L1 Cache
128 KB (per SM)
1024 KB
L2 Cache
88 MB

Theoretical Performance

22.80 GPixel/s
Pixel Rate
483.8 GPixel/s
34.20 GTexel/s
Texture Rate
1613 GTexel/s
2.189 TFLOPS
FP16 (half)
103.2 TFLOPS
1094 GFLOPS
FP32 (float)
103.2 TFLOPS
34.20 GFLOPS
FP64 (double)
1.613 TFLOPS

Graphics Processor

TU117
GPU Name
GB202
-
GPU Variant
GB202
Turing
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
12 nm
Process Size
0 nm
4.7 billion
Transistors
Unknown
200 mm²
Die Size
Unknown

Board Design

30W
TDP
500W
200 W
Suggested PSU
900 W
3x mini-DisplayPort 1.4a
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
None
Power Connectors
1x 16-pin

Graphics Features

12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
9.1
6.6
Shader Model
6.7

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy