AMD Instinct MI300A vs NVIDIA L4
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 24GB VRAM L4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 9 months late
Boost Clock has increased by 3% (2100MHz vs 2040MHz)
More VRAM (128GB vs 24GB)
Larger VRAM bandwidth (5300GB/s vs 300.1GB/s)
7168 additional rendering cores
NVIDIA L4 's Advantages
Lower TDP (72W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+304%
122.6 TFLOPS
L4
30.29 TFLOPS
Graphics Card
Dec 2023
Release Date
Mar 2023
Instinct
Generation
Tesla Ada(Lxx)
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1000 MHz
Base Clock
795 MHz
2100 MHz
Boost Clock
2040 MHz
5200 MHz
Memory Clock
1563 MHz
Memory
128GB
Memory Size
24GB
HBM3
Memory Type
GDDR6
8192bit
Memory Bus
192bit
5300GB/s
Bandwidth
300.1GB/s
Render Config
228
Compute Units
-
-
SM Count
60
14592
Shading Units
7424
880
TMUs
240
0
ROPs
80
-
Tensor Cores
240
-
RT Cores
60
16 KB (per CU)
L1 Cache
128 KB (per SM)
16 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
163.2 GPixel/s
1496 GTexel/s
Texture Rate
489.6 GTexel/s
980.6 TFLOPS
FP16 (half)
30.29 TFLOPS
122.6 TFLOPS
FP32 (float)
30.29 TFLOPS
61.3 TFLOPS
FP64 (double)
473.3 GFLOPS
Board Design
760W
TDP
72W
1000 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
MI300
GPU Name
AD104
-
GPU Variant
AD104-???-A1
CDNA 3.0
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
146 billion
Transistors
35.8 billion
1017 mm²
Die Size
294 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
8.9
N/A
Shader Model
6.8
