NVIDIA GRID K100 vs NVIDIA L40
We compared two Professional market GPUs: 256MB VRAM GRID K100 and 48GB VRAM L40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K100 's Advantages
Lower TDP (130W vs 300W)
NVIDIA L40 's Advantages
Released 9 years and 4 months late
Boost Clock2490MHz
More VRAM (48GB vs 256GB)
Larger VRAM bandwidth (864.0GB/s vs 28.51GB/s)
17984 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K100
0.326 TFLOPS
L40
+27666%
90.52 TFLOPS
Graphics Card
Jun 2013
Release Date
Oct 2022
GRID
Generation
Tesla Ada
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
735 MHz
-
Boost Clock
2490 MHz
891 MHz
Memory Clock
2250 MHz
Memory
256MB
Memory Size
48GB
DDR3
Memory Type
GDDR6
128bit
Memory Bus
384bit
28.51GB/s
Bandwidth
864.0GB/s
Render Config
-
-
-
-
SM Count
142
192
Shading Units
18176
16
TMUs
568
16
ROPs
192
-
Tensor Cores
568
-
RT Cores
142
16 KB (per SMX)
L1 Cache
128 KB (per SM)
256 KB
L2 Cache
96 MB
-
-
-
Theoretical Performance
3.400 GPixel/s
Pixel Rate
478.1 GPixel/s
13.60 GTexel/s
Texture Rate
1414 GTexel/s
-
FP16 (half)
90.52 TFLOPS
326.4 GFLOPS
FP32 (float)
90.52 TFLOPS
13.60 GFLOPS
FP64 (double)
1414 GFLOPS
Board Design
130W
TDP
300W
300 W
Suggested PSU
700 W
No outputs
Outputs
4x DisplayPort 1.4a
-
Power Connectors
1x 16-pin
Graphics Processor
GK107
GPU Name
AD102
-
GPU Variant
AD102-895-A1
Kepler
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
28 nm
Process Size
4 nm
1.27 billion
Transistors
76.3 billion
118 mm²
Die Size
608 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.0
CUDA
8.9
5.1
Shader Model
6.6
