AMD Radeon Instinct MI8 vs NVIDIA RTX 4000 SFF Ada Generation
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 16GB VRAM RTX 4000 SFF Ada Generation to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
256 additional rendering cores
Lower TDP (175W vs 300W)
NVIDIA RTX 4000 SFF Ada Generation 's Advantages
Released 1 years and 11 months late
Boost Clock1746MHz
More VRAM (16GB vs 4GB)
Larger VRAM bandwidth (1.02TB/s vs 512.0GB/s)
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
8.192 TFLOPS
RTX 4000 SFF Ada Generation
+63%
13.41 TFLOPS
Graphics Card
Dec 2016
Release Date
Nov 2018
Radeon Instinct
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1200 MHz
-
Boost Clock
1746 MHz
500 MHz
Memory Clock
1000 MHz
Memory
4GB
Memory Size
16GB
HBM
Memory Type
HBM2
4096bit
Memory Bus
4096bit
512.0GB/s
Bandwidth
1.02TB/s
Render Config
64
Compute Units
60
-
SM Count
48
4096
Shading Units
3840
256
TMUs
240
64
ROPs
64
-
Tensor Cores
192
-
RT Cores
48
16 KB (per CU)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
111.7 GPixel/s
256.0 GTexel/s
Texture Rate
419.0 GTexel/s
8.192 TFLOPS
FP16 (half)
26.82 TFLOPS
8.192 TFLOPS
FP32 (float)
13.41 TFLOPS
512.0 GFLOPS
FP64 (double)
6.705 TFLOPS
Board Design
175W
TDP
300W
450 W
Suggested PSU
700 W
No outputs
Outputs
1x mini-DisplayPort 1.4a
1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
Fiji
GPU Name
Vega 20
Fiji XT CA
(215-0862120)
GPU Variant
Vega 20 GLXT
GCN 3.0
Architecture
GCN 5.1
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
8.9 billion
Transistors
13.23 billion
596 mm²
Die Size
331 mm²
Graphics Features
12 (12_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
2.1
OpenCL
2.1
1.2.170
Vulkan
1.3
-
CUDA
8.9
6.5
Shader Model
6.7
