NVIDIA L4 vs NVIDIA A10G
We compared two Professional market GPUs: 24GB VRAM L4 and 12GB VRAM A10G to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L4 's Advantages
Released 1 years and 11 months late
Boost Clock has increased by 19% (2040MHz vs 1710MHz)
More VRAM (24GB vs 12GB)
Lower TDP (72W vs 150W)
NVIDIA A10G 's Advantages
Larger VRAM bandwidth (600.2GB/s vs 300.1GB/s)
1792 additional rendering cores
Score
Benchmark
FP32 (float)
L4
30.29 TFLOPS
A10G
+4%
31.52 TFLOPS
Graphics Card
Mar 2023
Release Date
Apr 2021
Tesla Ada(Lxx)
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
795 MHz
Base Clock
1320 MHz
2040 MHz
Boost Clock
1710 MHz
1563 MHz
Memory Clock
1563 MHz
Memory
24GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
384bit
300.1GB/s
Bandwidth
600.2GB/s
Render Config
-
-
-
60
SM Count
72
7424
Shading Units
9216
240
TMUs
288
80
ROPs
96
240
Tensor Cores
288
60
RT Cores
72
128 KB (per SM)
L1 Cache
128 KB (per SM)
48 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
163.2 GPixel/s
Pixel Rate
164.2 GPixel/s
489.6 GTexel/s
Texture Rate
492.5 GTexel/s
30.29 TFLOPS
FP16 (half)
31.52 TFLOPS
30.29 TFLOPS
FP32 (float)
31.52 TFLOPS
473.3 GFLOPS
FP64 (double)
985.0 GFLOPS
Board Design
72W
TDP
150W
250 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
None
Power Connectors
8-pin EPS
Graphics Processor
AD104
GPU Name
GA102
AD104-???-A1
GPU Variant
GA102-890-A1
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
35.8 billion
Transistors
28.3 billion
294 mm²
Die Size
628 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
8.6
6.8
Shader Model
6.6
