GeForce RTX 4090 vs Radeon Pro W6600
Aggregate performance score
We've compared Radeon Pro W6600 with GeForce RTX 4090, including specs and performance data.
RTX 4090 outperforms Pro W6600 by a whopping 154% 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 | 159 | 3 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 23.94 | 30.91 |
| Power efficiency | 27.83 | 15.73 |
| Architecture | RDNA 2.0 (2020−2025) | Ada Lovelace (2022−2024) |
| GPU code name | Navi 23 | AD102 |
| Market segment | Workstation | Desktop |
| Release date | 8 June 2021 (5 years ago) | 20 September 2022 (4 years ago) |
| Launch price (MSRP) | $649 | $1,599 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
RTX 4090 has 29% better value for money than Pro W6600.
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 | 1792 | 16384 |
| Core clock speed | 2331 MHz | 2235 MHz |
| Boost clock speed | 2903 MHz | 2520 MHz |
| Number of transistors | 11,060 million | 76,300 million |
| Manufacturing process technology | 7 nm | 5 nm |
| Power consumption (TDP) | 100 Watt | 450 Watt |
| Texture fill rate | 325.1 | 1,290.2 |
| Floating-point processing power | 10.4 TFLOPS | 82.58 TFLOPS |
| ROPs | 64 | 176 |
| TMUs | 112 | 512 |
| Tensor Cores | no data | 512 |
| Ray Tracing Cores | 28 | 128 |
| L0 Cache | 448 KB | no data |
| L1 Cache | 512 KB | 16 MB |
| L2 Cache | 2 MB | 72 MB |
| L3 Cache | 32 MB | no data |
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 4.0 x16 | PCIe 4.0 x16 |
| Length | 241 mm | 304 mm |
| Width | 1-slot | 3-slot |
| Supplementary power connectors | 1x 6-pin | 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 | GDDR6 | GDDR6X |
| Maximum RAM amount | 8 GB | 24 GB |
| Memory bus width | 128 Bit | 384 Bit |
| Memory clock speed | 1750 MHz | 1313 MHz |
| Memory bandwidth | 224.0 GB/s | 1.01 TB/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 | 4x DisplayPort | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12.0 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.5 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.4 |
| CUDA | - | 8.9 |
| 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 | 95−100
−61.4%
| 246 |
| 1440p | 70−75
−62%
| 184 |
| 4K | 50−55
−62.7%
| 134 |
Cost per frame, $
| 1080p | 6.83 | 6.50
+4.9%
|
| 1440p | 9.27 | 8.69
+6.3%
|
| 4K | 12.98 | 11.93
+8.1%
|
- Pro W6600 and RTX 4090 have nearly equal cost per frame in 1080p
- RTX 4090 has 6% lower cost per frame in 1440p
- RTX 4090 has 8% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Atomic Heart | 324 | 324 |
| Counter-Strike 2 | 351 | 351 |
| Cyberpunk 2077 | 227 | 227 |
| Resident Evil 4 Remake | 351 | 351 |
Full HD
Medium
| Atomic Heart | 265 | 265 |
| Battlefield 5 | 190−200 | 190−200 |
| Counter-Strike 2 | 340 | 340 |
| Cyberpunk 2077 | 224 | 224 |
| Far Cry 5 | 209 | 209 |
| Fortnite | 300−350 | 300−350 |
| Forza Horizon 4 | 300−350 | 300−350 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 650−700 | 650−700 |
Full HD
High
| Atomic Heart | 234 | 234 |
| Battlefield 5 | 190−200 | 190−200 |
| Counter-Strike 2 | 340 | 340 |
| Counter-Strike: Global Offensive | 270−280 | 270−280 |
| Cyberpunk 2077 | 215 | 215 |
| Dota 2 | 253 | 253 |
| Far Cry 5 | 201 | 201 |
| Fortnite | 300−350 | 300−350 |
| Forza Horizon 4 | 300−350 | 300−350 |
| Grand Theft Auto V | 174 | 174 |
| Metro Exodus | 230 | 230 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 578 | 578 |
| Valorant | 650−700 | 650−700 |
Full HD
Ultra
| Battlefield 5 | 190−200 | 190−200 |
| Cyberpunk 2077 | 211 | 211 |
| Dota 2 | 224 | 224 |
| Far Cry 5 | 187 | 187 |
| Forza Horizon 4 | 300−350 | 300−350 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 305 | 305 |
| Valorant | 680 | 680 |
Full HD
Epic
| Fortnite | 300−350 | 300−350 |
1440p
High
| Counter-Strike 2 | 312 | 312 |
| Counter-Strike: Global Offensive | 500−550 | 500−550 |
| Grand Theft Auto V | 162 | 162 |
| Metro Exodus | 180 | 180 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 450−500 | 450−500 |
1440p
Ultra
| Battlefield 5 | 190−200 | 190−200 |
| Cyberpunk 2077 | 159 | 159 |
| Far Cry 5 | 187 | 187 |
| Forza Horizon 4 | 300−350 | 300−350 |
| The Witcher 3: Wild Hunt | 262 | 262 |
1440p
Epic
| Fortnite | 150−160 | 150−160 |
4K
High
| Atomic Heart | 102 | 102 |
| Counter-Strike 2 | 166 | 166 |
| Grand Theft Auto V | 187 | 187 |
| Metro Exodus | 137 | 137 |
| The Witcher 3: Wild Hunt | 281 | 281 |
| Valorant | 300−350 | 300−350 |
4K
Ultra
| Battlefield 5 | 130−140 | 130−140 |
| Counter-Strike 2 | 140−150 | 140−150 |
| Cyberpunk 2077 | 81 | 81 |
| Dota 2 | 227 | 227 |
| Far Cry 5 | 170 | 170 |
| Forza Horizon 4 | 300−350 | 300−350 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100 | 95−100 |
4K
Epic
| Fortnite | 75−80 | 75−80 |
This is how Pro W6600 and RTX 4090 compete in popular games:
- RTX 4090 is 159% faster in 1080p
- RTX 4090 is 163% faster in 1440p
- RTX 4090 is 168% faster in 4K
All in all, in popular games:
- there's a draw in 62 tests (100%)
Pros & cons summary
| Performance score | 35.90 | 91.30 |
| Recency | 8 June 2021 | 20 September 2022 |
| Maximum RAM amount | 8 GB | 24 GB |
| Chip lithography | 7 nm | 5 nm |
| Power consumption (TDP) | 100 Watt | 450 Watt |
Pro W6600 has 78% lower power consumption.
RTX 4090, on the other hand, has a 154% higher aggregate performance score, an age advantage of 1 year, a 200% higher maximum VRAM amount, and a 29% more advanced lithography process.
The GeForce RTX 4090 is our recommended choice as it beats the Radeon Pro W6600 in performance tests.
Be aware that Radeon Pro W6600 is a workstation graphics card while GeForce RTX 4090 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.
