NVIDIA Tesla K20m vs NVIDIA L4
We compared two Professional market GPUs: 5GB VRAM Tesla K20m and 24GB VRAM L4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L4 's Advantages
Released 10 years and 2 months late
Boost Clock2040MHz
More VRAM (24GB vs 5GB)
Larger VRAM bandwidth (300.1GB/s vs 208.0GB/s)
4928 additional rendering cores
Lower TDP (72W vs 225W)
Score
Benchmark
FP32 (float)
Tesla K20m
3.524 TFLOPS
L4
+759%
30.29 TFLOPS
Graphics Card
Jan 2013
Release Date
Mar 2023
Tesla
Generation
Tesla Ada(Lxx)
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
795 MHz
-
Boost Clock
2040 MHz
1300 MHz
Memory Clock
1563 MHz
Memory
5GB
Memory Size
24GB
GDDR5
Memory Type
GDDR6
320bit
Memory Bus
192bit
208.0GB/s
Bandwidth
300.1GB/s
Render Config
-
-
-
-
SM Count
60
2496
Shading Units
7424
208
TMUs
240
40
ROPs
80
-
Tensor Cores
240
-
RT Cores
60
16 KB (per SMX)
L1 Cache
128 KB (per SM)
1280 KB
L2 Cache
48 MB
-
-
-
Theoretical Performance
36.71 GPixel/s
Pixel Rate
163.2 GPixel/s
146.8 GTexel/s
Texture Rate
489.6 GTexel/s
-
FP16 (half)
30.29 TFLOPS
3.524 TFLOPS
FP32 (float)
30.29 TFLOPS
1175 GFLOPS
FP64 (double)
473.3 GFLOPS
Board Design
225W
TDP
72W
550 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
GK110
GPU Name
AD104
-
GPU Variant
AD104-???-A1
Kepler
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
7.08 billion
Transistors
35.8 billion
561 mm²
Die Size
294 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
3.5
CUDA
8.9
5.1
Shader Model
6.8
