AMD Instinct MI300A vs NVIDIA Tesla T4
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 16GB VRAM Tesla T4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 5 years and 3 months late
Boost Clock has increased by 32% (2100MHz vs 1590MHz)
More VRAM (128GB vs 16GB)
Larger VRAM bandwidth (5300GB/s vs 320.0GB/s)
12032 additional rendering cores
NVIDIA Tesla T4 's Advantages
Lower TDP (70W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+1405%
122.6 TFLOPS
Tesla T4
8.141 TFLOPS
Graphics Card
Dec 2023
Release Date
Sep 2018
Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
585 MHz
2100 MHz
Boost Clock
1590 MHz
5200 MHz
Memory Clock
1250 MHz
Memory
128GB
Memory Size
16GB
HBM3
Memory Type
GDDR6
8192bit
Memory Bus
256bit
5300GB/s
Bandwidth
320.0GB/s
Render Config
228
Compute Units
-
-
SM Count
40
14592
Shading Units
2560
880
TMUs
160
0
ROPs
64
-
Tensor Cores
320
-
RT Cores
40
16 KB (per CU)
L1 Cache
64 KB (per SM)
16 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
101.8 GPixel/s
1496 GTexel/s
Texture Rate
254.4 GTexel/s
980.6 TFLOPS
FP16 (half)
65.13 TFLOPS
122.6 TFLOPS
FP32 (float)
8.141 TFLOPS
61.3 TFLOPS
FP64 (double)
254.4 GFLOPS
Board Design
760W
TDP
70W
1000 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
MI300
GPU Name
TU104
-
GPU Variant
TU104-895-A1
CDNA 3.0
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
146 billion
Transistors
13.6 billion
1017 mm²
Die Size
545 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
7.5
N/A
Shader Model
6.6
