NVIDIA RTX 4000 SFF Ada Generation vs AMD Radeon Instinct MI100
We compared two Professional market GPUs: 16GB VRAM RTX 4000 SFF Ada Generation and 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA RTX 4000 SFF Ada Generation 's Advantages
Boost Clock has increased by 16% (1746MHz vs 1502MHz)
AMD Radeon Instinct MI100 's Advantages
Released 2 years late
More VRAM (32GB vs 16GB)
Larger VRAM bandwidth (1229GB/s vs 1.02TB/s)
3840 additional rendering cores
Score
Benchmark
FP32 (float)
RTX 4000 SFF Ada Generation
13.41 TFLOPS
Radeon Instinct MI100
+72%
23.07 TFLOPS
Graphics Card
Nov 2018
Release Date
Nov 2020
Radeon Instinct
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1200 MHz
Base Clock
1000 MHz
1746 MHz
Boost Clock
1502 MHz
1000 MHz
Memory Clock
1200 MHz
Memory
16GB
Memory Size
32GB
HBM2
Memory Type
HBM2
4096bit
Memory Bus
4096bit
1.02TB/s
Bandwidth
1229GB/s
Render Config
60
Compute Units
120
48
SM Count
-
3840
Shading Units
7680
240
TMUs
480
64
ROPs
64
192
Tensor Cores
-
48
RT Cores
-
16 KB (per CU)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
8 MB
-
-
-
Theoretical Performance
111.7 GPixel/s
Pixel Rate
96.13 GPixel/s
419.0 GTexel/s
Texture Rate
721.0 GTexel/s
26.82 TFLOPS
FP16 (half)
184.6 TFLOPS
13.41 TFLOPS
FP32 (float)
23.07 TFLOPS
6.705 TFLOPS
FP64 (double)
11.54 TFLOPS
Board Design
300W
TDP
300W
700 W
Suggested PSU
700 W
1x mini-DisplayPort 1.4a
Outputs
No outputs
2x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
Vega 20
GPU Name
Arcturus
Vega 20 GLXT
GPU Variant
Arcturus XL
GCN 5.1
Architecture
CDNA 1.0
TSMC
Foundry
TSMC
7 nm
Process Size
7 nm
13.23 billion
Transistors
25.6 billion
331 mm²
Die Size
750 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
2.1
OpenCL
2.1
1.3
Vulkan
N/A
8.9
CUDA
-
6.7
Shader Model
N/A
