NVIDIA Quadro RTX 4000 vs AMD Radeon Instinct MI60
We compared two Professional market GPUs: 8GB VRAM Quadro RTX 4000 and 32GB VRAM Radeon Instinct MI60 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Quadro RTX 4000 's Advantages
Lower TDP (160W vs 300W)
AMD Radeon Instinct MI60 's Advantages
Boost Clock has increased by 17% (1800MHz vs 1545MHz)
More VRAM (32GB vs 8GB)
Larger VRAM bandwidth (1024GB/s vs 416.0GB/s)
1792 additional rendering cores
Score
Benchmark
FP32 (float)
Quadro RTX 4000
7.119 TFLOPS
Radeon Instinct MI60
+107%
14.75 TFLOPS
Graphics Card
Nov 2018
Release Date
Nov 2018
Quadro
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1005 MHz
Base Clock
1200 MHz
1545 MHz
Boost Clock
1800 MHz
1625 MHz
Memory Clock
1000 MHz
Memory
8GB
Memory Size
32GB
GDDR6
Memory Type
HBM2
256bit
Memory Bus
4096bit
416.0GB/s
Bandwidth
1024GB/s
Render Config
-
Compute Units
64
36
SM Count
-
2304
Shading Units
4096
144
TMUs
256
64
ROPs
64
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
98.88 GPixel/s
Pixel Rate
115.2 GPixel/s
222.5 GTexel/s
Texture Rate
460.8 GTexel/s
14.24 TFLOPS
FP16 (half)
29.49 TFLOPS
7.119 TFLOPS
FP32 (float)
14.75 TFLOPS
222.5 GFLOPS
FP64 (double)
7.373 TFLOPS
Board Design
160W
TDP
300W
450 W
Suggested PSU
700 W
3x DisplayPort 1.4a
1x USB Type-C
Outputs
1x mini-DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
TU104
GPU Name
Vega 20
TU104-850-A1
GPU Variant
Vega 20 GL
Turing
Architecture
GCN 5.1
TSMC
Foundry
TSMC
12 nm
Process Size
7 nm
13.6 billion
Transistors
13.23 billion
545 mm²
Die Size
331 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
7.5
CUDA
-
6.6
Shader Model
6.4
