L4 vs Radeon Instinct MI25
We compared two Professional market GPUs: 24GB VRAM L4 and 16GB VRAM Radeon Instinct MI25 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L4 's Advantages
Released 5 years and 9 months late
Boost Clock has increased by 36% (2040MHz vs 1500MHz)
More VRAM (24GB vs 16GB)
3328 additional rendering cores
Lower TDP (72W vs 300W)
Radeon Instinct MI25 's Advantages
Larger VRAM bandwidth (436.2GB/s vs 300.1GB/s)
Score
Benchmark
FP32 (float)
L4
+146%
30290
Radeon Instinct MI25
12290
Graphics Card
Mar 2023
Release Date
Jun 2017
Tesla Ada(Lxx)
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
795 MHz
Base Clock
1400 MHz
2040 MHz
Boost Clock
1500 MHz
1563 MHz
Memory Clock
852 MHz
Memory
24GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
192bit
Memory Bus
2048bit
300.1GB/s
Bandwidth
436.2GB/s
Render Config
-
Compute Units
64
60
SM Count
-
7424
Shading Units
4096
240
TMUs
256
80
ROPs
64
240
Tensor Cores
-
60
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
4 MB
Theoretical Performance
163.2 GPixel/s
Pixel Rate
96.00 GPixel/s
489.6 GTexel/s
Texture Rate
384.0 GTexel/s
30.29 TFLOPS
FP16 (half)
24.58 TFLOPS
30.29 TFLOPS
FP32 (float)
12.29 TFLOPS
473.3 GFLOPS
FP64 (double)
768.0 GFLOPS
Board Design
72W
TDP
300W
250 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
None
Power Connectors
2x 8-pin
Graphics Processor
AD104
GPU Name
Vega 10
AD104-???-A1
GPU Variant
Vega 10 XT GL
(215-0894124)
Ada Lovelace
Architecture
GCN 5.0
TSMC
Foundry
GlobalFoundries
5 nm
Process Size
14 nm
35.8 billion
Transistors
12.5 billion
294 mm²
Die Size
495 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
8.9
CUDA
-
6.8
Shader Model
6.4
