AMD Radeon Instinct MI6 vs NVIDIA RTX 4000 SFF Ada Generation
We compared two Professional market GPUs: 8GB VRAM Radeon Instinct MI6 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 MI6 's Advantages
Lower TDP (150W vs 300W)
NVIDIA RTX 4000 SFF Ada Generation 's Advantages
Released 1 years and 11 months late
Boost Clock has increased by 42% (1746MHz vs 1233MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (1.02TB/s vs 224.0GB/s)
1536 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI6
5.682 TFLOPS
RTX 4000 SFF Ada Generation
+136%
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
1120 MHz
Base Clock
1200 MHz
1233 MHz
Boost Clock
1746 MHz
1750 MHz
Memory Clock
1000 MHz
Memory
8GB
Memory Size
16GB
GDDR5
Memory Type
HBM2
256bit
Memory Bus
4096bit
224.0GB/s
Bandwidth
1.02TB/s
Render Config
36
Compute Units
60
-
SM Count
48
2304
Shading Units
3840
144
TMUs
240
32
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
39.46 GPixel/s
Pixel Rate
111.7 GPixel/s
177.6 GTexel/s
Texture Rate
419.0 GTexel/s
5.682 TFLOPS
FP16 (half)
26.82 TFLOPS
5.682 TFLOPS
FP32 (float)
13.41 TFLOPS
355.1 GFLOPS
FP64 (double)
6.705 TFLOPS
Board Design
150W
TDP
300W
450 W
Suggested PSU
700 W
No outputs
Outputs
1x mini-DisplayPort 1.4a
1x 6-pin
Power Connectors
2x 8-pin
Graphics Processor
Ellesmere
GPU Name
Vega 20
Ellesmere XT
GPU Variant
Vega 20 GLXT
GCN 4.0
Architecture
GCN 5.1
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
7 nm
5.7 billion
Transistors
13.23 billion
232 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
Vulkan
1.3
-
CUDA
8.9
6.4
Shader Model
6.7
