NVIDIA Tesla K40st vs NVIDIA GeForce RTX 5090 D
GPU · Specs Compare
Graphics Card
Release Date
Nov 2013
Jan 2025
Generation
Tesla
GeForce 50
Type
Professional
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Memory Clock
1502 MHz
1750 MHz
Base Clock
—
2017 MHz
Boost Clock
—
2407 MHz
Memory
Memory Size
12GB
32GB
Memory Type
GDDR5
GDDR7
Memory Bus
384bit
512bit
Bandwidth
288.4GB/s
1.79TB/s
Render Config
Shading Units
2880
21760
TMUs
240
680
ROPs
48
176
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
1536 KB
96 MB
SM Count
—
170
Tensor Cores
—
680
RT Cores
—
170
Theoretical Performance
Pixel Rate
34.50 GPixel/s
423.6 GPixel/s
Texture Rate
138.0 GTexel/s
1636.8 GTexel/s
FP32 (float)
3.312 TFLOPS
104.8 TFLOPS
FP64 (double)
1104 GFLOPS
1.637 TFLOPS
FP16 (half)
—
104.8 TFLOPS
Graphics Processor
GPU Name
GK110B
GB202
Architecture
Kepler
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
28 nm
5 nm
Transistors
7.08 billion
92.2 billion
Die Size
561 mm²
750 mm²
GPU Variant
—
GB202-250-A1
Board Design
TDP
245W
575W
Suggested PSU
550 W
950 W
Outputs
No outputs
1x HDMI 2.1b3x DisplayPort 2.1b
Power Connectors
—
1x 16-pin
Graphics Features
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
1.4
CUDA
3.5
12.0
Shader Model
5.1
6.8
Benchmark
3DMark Time Spy
—
48,052
3DMark Time Spy Extreme
—
25,999
3DMark Speed Way
—
14,790
▲ Specs Compare
Data sourced from official specifications and benchmark tests.