Explore the complete details of Radeon Pro Vega II Duo VS GeForce RTX 3090, including specs, performance benchmarks
GeForce RTX 5090
NVIDIAGeForce RTX 4090
NVIDIAQuadro K5000
NVIDIAIris Xe Graphics G7
IntelGraphics 4-Cores iGPU (Arc)
IntelGeForce GTX 570
NVIDIAGraphics 4-Core iGPU (Arc)
UnknownGeForce GTX 750 Ti
NVIDIARadeon RX 460 Mobile
AMDGRID M60-8Q
NVIDIARadeon HD 7850
AMDRadeon HD 8970M
AMDThe Radeon Pro Vega II Duo GPU by AMD. features a GCN 5.1 (2018−2022) architecture. with 4096 ×2 CUDA cores. and a boost clock of 1720 MHz MHz. It offers HBM2 memory with 32 GB ×2 GB capacity and a 4096 Bit ×2-bit interface. delivering a bandwidth of 1.02 TB/s ×2 GB/s. With a power consumption (TDP) of 475W. it supports DirectX 12 (12_1), Vulkan 1.3 for enhanced performance.
The Radeon Pro Vega II Duo GPU by AMD. features a GCN 5.1 (2018−2022) architecture. with 4096 ×2 CUDA cores. and a boost clock of 1720 MHz MHz. It offers HBM2 memory with 32 GB ×2 GB capacity and a 4096 Bit ×2-bit interface. delivering a bandwidth of 1.02 TB/s ×2 GB/s. With a power consumption (TDP) of 475W. it supports DirectX 12 (12_1), Vulkan 1.3 for enhanced performance.
Basic details about the Radeon Pro Vega II Duo, including manufacturer, ranking, and release date.
![]() |
|
|
---|---|---|
Manufacturer | AMD | NVIDIA |
Ranking | 164 | 34 |
Popularity Rank | not in top-100 | not in top-100 |
Architecture | GCN 5.1 (2018−2022) | Ampere (2020−2025) |
GPU code name | Vega 20 | GA102 |
Market Segmente | Workstation | Desktop |
Length - Width | N/A - Quad-slot | 336 mm - 3-slot |
Release Date | 3 June 2019 | 1 September 2020 |
PerformanceDetails on clock speeds, cores, and floating-point processing power of Radeon Pro Vega II Duo VS GeForce RTX 3090. |
||
Core Clock Speed | 1400 MHz | 1395 MHz |
Boost Clock Speed | 1720 MHz | 1695 MHz |
Floating Point Processing Power | 14.09 TFLOPS ×2 | 35.58 TFLOPS |
No of Transistors | 13,230 million | 28,300 million |
CUDA Cores | 4096 ×2 | 10496 |
Ray Tracing Cores | N/A | 82 |
Tensor Cores | N/A | 328 |
Texture Fill Rate | 440.3 ×2 | 556.0 |
ROPs | 64 ×2 | 112 |
Available display connectors and API compatibility for enhanced performance.
![]() |
|
|
---|---|---|
Interface | Apple MPX | PCIe 4.0 x16 |
Display Connectors | 1x HDMI 2.0b, 4x Thunderbolt | 1x HDMI, 3x DisplayPort |
HDMI | 1 | 1 |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
Shader Model | 6.7 | 6.5 |
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 2.0 |
Vulkan | 1.3 | 1.2 |
CUDA | N/A | 8.5 |
DLSS | N/A | 1 |
TMUs | 256 ×2 | 328 |
Memory & BusInformation on memory type, capacity, and bandwidth to evaluate data processing power. |
||
Memory Type | HBM2 | GDDR6X |
Maximum RAM | 32 GB ×2 | 24 GB |
Memory Bus Width | 4096 Bit ×2 | 384 Bit |
Memory Clock Speed | 1000 MHz | 1219 MHz |
Memory Bandwidth | 1.02 TB/s ×2 GB/s | 936.2 GB/s GB/s |
Resizable BAR | N/A | 1 |
Power & EfficiencyPower consumption, efficiency, and additional power requirements. |
||
Power Consumption (TDP) | 475 W | 350 W |
Power Efficiency | 5.31 | 13.71 |
Manufacturing Process | 7 nm | 8 nm |
Supplementary Power Connectors | None | 1x 12-pin |
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.