AMD Instinct MI300A vs NVIDIA GRID RTX T10 4
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 4GB VRAM GRID RTX T10 4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 3 years and 11 months late
Boost Clock has increased by 51% (2100MHz vs 1395MHz)
More VRAM (128GB vs 4GB)
Larger VRAM bandwidth (5300GB/s vs 672.0GB/s)
11008 additional rendering cores
NVIDIA GRID RTX T10 4 's Advantages
Lower TDP (150W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+1126%
122.6 TFLOPS
GRID RTX T10 4
9.999 TFLOPS
Graphics Card
Dec 2023
Release Date
Jan 2020
Instinct
Generation
GRID
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
1065 MHz
2100 MHz
Boost Clock
1395 MHz
5200 MHz
Memory Clock
1750 MHz
Memory
128GB
Memory Size
4GB
HBM3
Memory Type
GDDR6
8192bit
Memory Bus
384bit
5300GB/s
Bandwidth
672.0GB/s
Render Config
228
Compute Units
-
-
SM Count
56
14592
Shading Units
3584
880
TMUs
224
0
ROPs
64
-
Tensor Cores
448
-
RT Cores
56
16 KB (per CU)
L1 Cache
64 KB (per SM)
16 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
89.28 GPixel/s
1496 GTexel/s
Texture Rate
312.5 GTexel/s
980.6 TFLOPS
FP16 (half)
20.00 TFLOPS
122.6 TFLOPS
FP32 (float)
9.999 TFLOPS
61.3 TFLOPS
FP64 (double)
312.5 GFLOPS
Board Design
760W
TDP
150W
1000 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
MI300
GPU Name
TU102
-
GPU Variant
TU102-875-A1
CDNA 3.0
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
146 billion
Transistors
18.6 billion
1017 mm²
Die Size
754 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
6.8
