L4 vs Data Center GPU Max Subsystem
We compared two Professional market GPUs: 24GB VRAM L4 and 128GB VRAM Data Center GPU Max Subsystem to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L4 's Advantages
Boost Clock has increased by 28% (2040MHz vs 1600MHz)
Lower TDP (72W vs 2400W)
Data Center GPU Max Subsystem 's Advantages
More VRAM (128GB vs 24GB)
Larger VRAM bandwidth (3205GB/s vs 300.1GB/s)
8960 additional rendering cores
Score
Benchmark
FP32 (float)
L4
30290
Data Center GPU Max Subsystem
+73%
52430
Graphics Card
Mar 2023
Release Date
Jan 2023
Tesla Ada(Lxx)
Generation
Data Center GPU
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
795 MHz
Base Clock
900 MHz
2040 MHz
Boost Clock
1600 MHz
1563 MHz
Memory Clock
1565 MHz
Memory
24GB
Memory Size
128GB
GDDR6
Memory Type
HBM2e
192bit
Memory Bus
8192bit
300.1GB/s
Bandwidth
3205GB/s
Render Config
60
SM Count
-
7424
Shading Units
16384
240
TMUs
1024
80
ROPs
0
240
Tensor Cores
1024
60
RT Cores
128
128 KB (per SM)
L1 Cache
64 KB (per EU)
48 MB
L2 Cache
408 MB
Theoretical Performance
163.2 GPixel/s
Pixel Rate
0 MPixel/s
489.6 GTexel/s
Texture Rate
1638 GTexel/s
30.29 TFLOPS
FP16 (half)
52.43 TFLOPS
30.29 TFLOPS
FP32 (float)
52.43 TFLOPS
473.3 GFLOPS
FP64 (double)
52.43 TFLOPS
Board Design
72W
TDP
2400W
250 W
Suggested PSU
2800 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 16-pin
Graphics Processor
AD104
GPU Name
Ponte Vecchio
AD104-???-A1
GPU Variant
-
Ada Lovelace
Architecture
Generation 12.5
TSMC
Foundry
Intel
5 nm
Process Size
10 nm
35.8 billion
Transistors
100 billion
294 mm²
Die Size
1280 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.9
CUDA
-
6.8
Shader Model
6.6
