Radeon PRO W7900 Dual Slot vs GeForce RTX 5090
Aggregate performance score
We've compared GeForce RTX 5090 with Radeon PRO W7900 Dual Slot, including specs and performance data.
RTX 5090 outperforms PRO W7900 Dual Slot by a whopping 196% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 2 | 204 |
| Place by popularity | 11 | not in top-100 |
| Cost-effectiveness evaluation | 24.42 | 4.15 |
| Power efficiency | 12.61 | 8.31 |
| Architecture | Blackwell 2.0 (2025−2026) | RDNA 3 (2023−2025) |
| GPU code name | GB202 | Navi 31 |
| Market segment | Desktop | Workstation |
| Release date | 30 January 2025 (1 year ago) | 19 June 2024 (2 years ago) |
| Launch price (MSRP) | $1,999 | $3,499 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
RTX 5090 has 488% better value for money than PRO W7900 Dual Slot.
Performance to price scatter graph
Currently popular graphics cards are shown for comparison.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 21760 | 6144 |
| Core clock speed | 2017 MHz | 1760 MHz |
| Boost clock speed | 2407 MHz | 2495 MHz |
| Number of transistors | 92,200 million | 57.7 billion |
| Manufacturing process technology | 5 nm | 5 nm |
| Power consumption (TDP) | 575 Watt | 295 Watt |
| Texture fill rate | 1,636.8 | 958.1 |
| Floating-point processing power | 104.8 TFLOPS | no data |
| ROPs | 176 | 192 |
| TMUs | 680 | 384 |
| Tensor Cores | 680 | no data |
| Ray Tracing Cores | 170 | 96 |
| L0 Cache | no data | 3 MB |
| L1 Cache | 21.3 MB | 3 MB |
| L2 Cache | 96 MB | 6 MB |
| L3 Cache | no data | 96 MB |
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 | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Length | 304 mm | 280 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 16-pin | 2x 8-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 | GDDR7 | GDDR6 |
| Maximum RAM amount | 32 GB | 48 GB |
| Memory bus width | 512 Bit | 384 Bit |
| Memory clock speed | 1750 MHz | 2250 MHz |
| Memory bandwidth | 1.79 TB/s | 864.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | + | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x HDMI 2.1b, 3x DisplayPort 2.1b | 3x DisplayPort 2.1, 1x mini-DisplayPort 2.1 |
| HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.8 | 6.9 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.0 |
| Vulkan | 1.4 | 1.4 |
| CUDA | 12.0 | - |
| DLSS | + | - |
Synthetic benchmarks
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 | 227 | 75−80
−67%
|
| 1440p | 189 | 60−65
−68.3%
|
| 4K | 145 | 45−50
−69%
|
Cost per frame, $
| 1080p | 8.81
+81.1%
| 46.65 |
| 1440p | 10.58
+81.9%
| 58.32 |
| 4K | 13.79
+82.3%
| 77.76 |
- RTX 5090 has 81% lower cost per frame in 1080p
- RTX 5090 has 82% lower cost per frame in 1440p
- RTX 5090 has 82% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 300−350
+203%
|
110−120 |
| Cyberpunk 2077 | 240−250
+208%
|
80−85 |
| Hogwarts Legacy | 170−180
+211%
|
55−60 |
| Resident Evil 4 Remake | 300−350
+205%
|
100−105 |
Full HD
Medium
| Battlefield 5 | 190−200
+203%
|
65−70 |
| Counter-Strike 2 | 300−350
+203%
|
110−120 |
| Cyberpunk 2077 | 240−250
+208%
|
80−85 |
| Far Cry 5 | 240−250
+206%
|
80−85 |
| Fortnite | 300−350
+202%
|
100−105 |
| Forza Horizon 4 | 300−350
+213%
|
110−120 |
| Hogwarts Legacy | 170−180
+211%
|
55−60 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+215%
|
55−60 |
| Valorant | 650−700
+209%
|
220−230 |
Full HD
High
| Battlefield 5 | 190−200
+203%
|
65−70 |
| Counter-Strike 2 | 300−350
+203%
|
110−120 |
| Counter-Strike: Global Offensive | 270−280
+209%
|
90−95 |
| Cyberpunk 2077 | 240−250
+208%
|
80−85 |
| Far Cry 5 | 240−250
+206%
|
80−85 |
| Fortnite | 300−350
+202%
|
100−105 |
| Forza Horizon 4 | 300−350
+213%
|
110−120 |
| Grand Theft Auto V | 170−180
+216%
|
55−60 |
| Hogwarts Legacy | 170−180
+211%
|
55−60 |
| Metro Exodus | 69
+229%
|
21−24 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+215%
|
55−60 |
| The Witcher 3: Wild Hunt | 400−450
+197%
|
150−160 |
| Valorant | 650−700
+209%
|
220−230 |
Full HD
Ultra
| Battlefield 5 | 190−200
+203%
|
65−70 |
| Cyberpunk 2077 | 240−250
+208%
|
80−85 |
| Far Cry 5 | 309
+209%
|
100−105 |
| Forza Horizon 4 | 300−350
+213%
|
110−120 |
| Hogwarts Legacy | 166
+202%
|
55−60 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+215%
|
55−60 |
| The Witcher 3: Wild Hunt | 352
+220%
|
110−120 |
| Valorant | 650−700
+209%
|
220−230 |
Full HD
Epic
| Fortnite | 300−350
+202%
|
100−105 |
1440p
High
| Counter-Strike 2 | 300−350
+212%
|
100−105 |
| Counter-Strike: Global Offensive | 500−550
+204%
|
170−180 |
| Grand Theft Auto V | 160−170
+207%
|
55−60 |
| Metro Exodus | 202
+211%
|
65−70 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+218%
|
55−60 |
| Valorant | 450−500
+203%
|
160−170 |
1440p
Ultra
| Battlefield 5 | 190−200
+202%
|
65−70 |
| Cyberpunk 2077 | 150−160
+218%
|
50−55 |
| Far Cry 5 | 304
+204%
|
100−105 |
| Forza Horizon 4 | 300−350
+206%
|
100−105 |
| Hogwarts Legacy | 160
+220%
|
50−55 |
| The Witcher 3: Wild Hunt | 321
+221%
|
100−105 |
1440p
Epic
| Fortnite | 150−160
+202%
|
50−55 |
4K
High
| Counter-Strike 2 | 87
+222%
|
27−30 |
| Grand Theft Auto V | 180−190
+212%
|
60−65 |
| Hogwarts Legacy | 136
+202%
|
45−50 |
| Metro Exodus | 167
+204%
|
55−60 |
| The Witcher 3: Wild Hunt | 383
+219%
|
120−130 |
| Valorant | 300−350
+218%
|
100−105 |
4K
Ultra
| Battlefield 5 | 130−140
+202%
|
45−50 |
| Counter-Strike 2 | 150−160
+210%
|
50−55 |
| Cyberpunk 2077 | 80−85
+196%
|
27−30 |
| Far Cry 5 | 231
+208%
|
75−80 |
| Forza Horizon 4 | 300−350
+205%
|
100−105 |
| Hogwarts Legacy | 102
+240%
|
30−33 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+220%
|
30−33 |
4K
Epic
| Fortnite | 75−80
+229%
|
24−27 |
This is how RTX 5090 and PRO W7900 Dual Slot compete in popular games:
- RTX 5090 is 203% faster in 1080p
- RTX 5090 is 215% faster in 1440p
- RTX 5090 is 222% faster in 4K
Pros & cons summary
| Performance score | 92.97 | 31.44 |
| Recency | 30 January 2025 | 19 June 2024 |
| Maximum RAM amount | 32 GB | 48 GB |
| Power consumption (TDP) | 575 Watt | 295 Watt |
RTX 5090 has a 196% higher aggregate performance score, and an age advantage of 7 months.
PRO W7900 Dual Slot, on the other hand, has a 50% higher maximum VRAM amount, and 49% lower power consumption.
The GeForce RTX 5090 is our recommended choice as it beats the Radeon PRO W7900 Dual Slot in performance tests.
Be aware that GeForce RTX 5090 is a desktop graphics card while Radeon PRO W7900 Dual Slot is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
