GeForce RTX 3090 Ti vs Radeon Pro Vega II Duo
Aggregate performance score
We've compared Radeon Pro Vega II Duo with GeForce RTX 3090 Ti, including specs and performance data.
RTX 3090 Ti outperforms Pro Vega II Duo by a whopping 111% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 138 | 13 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 7.59 | 8.30 |
| Power efficiency | 5.26 | 11.73 |
| Architecture | GCN 5.1 (2018−2022) | Ampere (2020−2024) |
| GPU code name | Vega 20 | GA102 |
| Market segment | Workstation | Desktop |
| Release date | 3 June 2019 (5 years ago) | 27 January 2022 (3 years ago) |
| Launch price (MSRP) | $4,399 | $1,999 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
RTX 3090 Ti has 9% better value for money than Pro Vega II Duo.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 4096 ×2 | 10752 |
| Core clock speed | 1400 MHz | 1560 MHz |
| Boost clock speed | 1720 MHz | 1860 MHz |
| Number of transistors | 13,230 million | 28,300 million |
| Manufacturing process technology | 7 nm | 8 nm |
| Power consumption (TDP) | 475 Watt | 450 Watt |
| Texture fill rate | 440.3 ×2 | 625.0 |
| Floating-point processing power | 14.09 TFLOPS ×2 | 40 TFLOPS |
| ROPs | 64 ×2 | 112 |
| TMUs | 256 ×2 | 336 |
| Tensor Cores | no data | 336 |
| Ray Tracing Cores | no data | 84 |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | Apple MPX | PCIe 4.0 x16 |
| Length | no data | 336 mm |
| Width | Quad-slot | 3-slot |
| Supplementary power connectors | None | 1x 16-pin |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | HBM2 | GDDR6X |
| Maximum RAM amount | 32 GB ×2 | 24 GB |
| Memory bus width | 4096 Bit ×2 | 384 Bit |
| Memory clock speed | 1000 MHz | 1313 MHz |
| Memory bandwidth | 1.02 TB/s ×2 | 1,008 GB/s |
| Shared memory | - | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | 1x HDMI 2.0b, 4x Thunderbolt | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | + | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| Shader Model | 6.7 | 6.6 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | - | 8.6 |
| DLSS | - | + |
Synthetic benchmark performance
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 95−100
−121%
| 210
+121%
|
| 1440p | 65−70
−122%
| 144
+122%
|
| 4K | 45−50
−127%
| 102
+127%
|
Cost per frame, $
| 1080p | 46.31
−386%
| 9.52
+386%
|
| 1440p | 67.68
−388%
| 13.88
+388%
|
| 4K | 97.76
−399%
| 19.60
+399%
|
- RTX 3090 Ti has 386% lower cost per frame in 1080p
- RTX 3090 Ti has 388% lower cost per frame in 1440p
- RTX 3090 Ti has 399% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 210−220
+0%
|
210−220
+0%
|
| Counter-Strike 2 | 180−190
+0%
|
180−190
+0%
|
| Cyberpunk 2077 | 219
+0%
|
219
+0%
|
Full HD
Medium Preset
| Atomic Heart | 210−220
+0%
|
210−220
+0%
|
| Battlefield 5 | 180−190
+0%
|
180−190
+0%
|
| Counter-Strike 2 | 180−190
+0%
|
180−190
+0%
|
| Cyberpunk 2077 | 201
+0%
|
201
+0%
|
| Far Cry 5 | 180−190
+0%
|
180−190
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 280−290
+0%
|
280−290
+0%
|
| Forza Horizon 5 | 200
+0%
|
200
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 400−450
+0%
|
400−450
+0%
|
Full HD
High Preset
| Atomic Heart | 210−220
+0%
|
210−220
+0%
|
| Battlefield 5 | 180−190
+0%
|
180−190
+0%
|
| Counter-Strike 2 | 180−190
+0%
|
180−190
+0%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 173
+0%
|
173
+0%
|
| Dota 2 | 217
+0%
|
217
+0%
|
| Far Cry 5 | 180−190
+0%
|
180−190
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 280−290
+0%
|
280−290
+0%
|
| Forza Horizon 5 | 188
+0%
|
188
+0%
|
| Grand Theft Auto V | 170
+0%
|
170
+0%
|
| Metro Exodus | 178
+0%
|
178
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 394
+0%
|
394
+0%
|
| Valorant | 400−450
+0%
|
400−450
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 180−190
+0%
|
180−190
+0%
|
| Counter-Strike 2 | 180−190
+0%
|
180−190
+0%
|
| Cyberpunk 2077 | 152
+0%
|
152
+0%
|
| Dota 2 | 195
+0%
|
195
+0%
|
| Far Cry 5 | 180−190
+0%
|
180−190
+0%
|
| Forza Horizon 4 | 280−290
+0%
|
280−290
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 193
+0%
|
193
+0%
|
| Valorant | 400−450
+0%
|
400−450
+0%
|
Full HD
Epic Preset
| Fortnite | 300−350
+0%
|
300−350
+0%
|
1440p
High Preset
| Counter-Strike 2 | 80−85
+0%
|
80−85
+0%
|
| Counter-Strike: Global Offensive | 500−550
+0%
|
500−550
+0%
|
| Grand Theft Auto V | 151
+0%
|
151
+0%
|
| Metro Exodus | 125
+0%
|
125
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 180−190
+0%
|
180−190
+0%
|
| Cyberpunk 2077 | 104
+0%
|
104
+0%
|
| Far Cry 5 | 160−170
+0%
|
160−170
+0%
|
| Forza Horizon 4 | 250−260
+0%
|
250−260
+0%
|
| The Witcher 3: Wild Hunt | 170−180
+0%
|
170−180
+0%
|
1440p
Epic Preset
| Fortnite | 150−160
+0%
|
150−160
+0%
|
4K
High Preset
| Atomic Heart | 65−70
+0%
|
65−70
+0%
|
| Counter-Strike 2 | 55−60
+0%
|
55−60
+0%
|
| Grand Theft Auto V | 181
+0%
|
181
+0%
|
| Metro Exodus | 84
+0%
|
84
+0%
|
| The Witcher 3: Wild Hunt | 173
+0%
|
173
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
4K
Ultra Preset
| Battlefield 5 | 130−140
+0%
|
130−140
+0%
|
| Counter-Strike 2 | 55−60
+0%
|
55−60
+0%
|
| Cyberpunk 2077 | 53
+0%
|
53
+0%
|
| Dota 2 | 184
+0%
|
184
+0%
|
| Far Cry 5 | 110−120
+0%
|
110−120
+0%
|
| Forza Horizon 4 | 210−220
+0%
|
210−220
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+0%
|
95−100
+0%
|
4K
Epic Preset
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how Pro Vega II Duo and RTX 3090 Ti compete in popular games:
- RTX 3090 Ti is 121% faster in 1080p
- RTX 3090 Ti is 122% faster in 1440p
- RTX 3090 Ti is 127% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 36.03 | 76.12 |
| Recency | 3 June 2019 | 27 January 2022 |
| Maximum RAM amount | 32 GB | 24 GB |
| Chip lithography | 7 nm | 8 nm |
| Power consumption (TDP) | 475 Watt | 450 Watt |
Pro Vega II Duo has a 33.3% higher maximum VRAM amount, and a 14.3% more advanced lithography process.
RTX 3090 Ti, on the other hand, has a 111.3% higher aggregate performance score, an age advantage of 2 years, and 5.6% lower power consumption.
The GeForce RTX 3090 Ti is our recommended choice as it beats the Radeon Pro Vega II Duo in performance tests.
Be aware that Radeon Pro Vega II Duo is a workstation graphics card while GeForce RTX 3090 Ti is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
