NVIDIA Tesla M4 vs AMD Radeon Instinct MI100
We compared two Professional market GPUs: 4GB VRAM Tesla M4 and 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla M4 's Advantages
Lower TDP (50W vs 300W)
AMD Radeon Instinct MI100 's Advantages
Released 5 years late
Boost Clock has increased by 40% (1502MHz vs 1072MHz)
More VRAM (32GB vs 4GB)
Larger VRAM bandwidth (1229GB/s vs 88.00GB/s)
6656 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla M4
2.195 TFLOPS
Radeon Instinct MI100
+951%
23.07 TFLOPS
Graphics Card
Nov 2015
Release Date
Nov 2020
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
872 MHz
Base Clock
1000 MHz
1072 MHz
Boost Clock
1502 MHz
1375 MHz
Memory Clock
1200 MHz
Memory
4GB
Memory Size
32GB
GDDR5
Memory Type
HBM2
128bit
Memory Bus
4096bit
88.00GB/s
Bandwidth
1229GB/s
Render Config
-
Compute Units
120
-
-
-
1024
Shading Units
7680
64
TMUs
480
32
ROPs
64
-
-
-
-
-
-
48 KB (per SMM)
L1 Cache
16 KB (per CU)
1024 KB
L2 Cache
8 MB
-
-
-
Theoretical Performance
34.30 GPixel/s
Pixel Rate
96.13 GPixel/s
68.61 GTexel/s
Texture Rate
721.0 GTexel/s
-
FP16 (half)
184.6 TFLOPS
2.195 TFLOPS
FP32 (float)
23.07 TFLOPS
68.61 GFLOPS
FP64 (double)
11.54 TFLOPS
Board Design
50W
TDP
300W
250 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
-
Power Connectors
2x 8-pin
Graphics Processor
GM206
GPU Name
Arcturus
-
GPU Variant
Arcturus XL
Maxwell 2.0
Architecture
CDNA 1.0
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
2.94 billion
Transistors
25.6 billion
228 mm²
Die Size
750 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
2.1
1.3
Vulkan
N/A
5.2
CUDA
-
6.4
Shader Model
N/A
