RTX PRO 2000 Blackwell Mobile vs Radeon R9 M390X
Aggregate performance score
We've compared Radeon R9 M390X with RTX PRO 2000 Blackwell Mobile, including specs and performance data.
RTX PRO 2000 Blackwell Mobile outperforms R9 M390X by a whopping 287% 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 | 510 | 154 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 9.56 | 61.58 |
| Architecture | GCN 3.0 (2014−2019) | Blackwell 2.0 (2025−2026) |
| GPU code name | Amethyst | GB206 |
| Market segment | Laptop | Mobile workstation |
| Release date | 5 May 2015 (10 years ago) | 19 March 2025 (1 year ago) |
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 | 2048 | 3328 |
| Core clock speed | 723 MHz | 952 MHz |
| Boost clock speed | no data | 1657 MHz |
| Number of transistors | 5,000 million | 21,900 million |
| Manufacturing process technology | 28 nm | 5 nm |
| Power consumption (TDP) | 100 Watt | 45 Watt |
| Texture fill rate | 92.54 | 172.3 |
| Floating-point processing power | 2.961 TFLOPS | 11.03 TFLOPS |
| ROPs | 32 | 32 |
| TMUs | 128 | 104 |
| Tensor Cores | no data | 104 |
| Ray Tracing Cores | no data | 26 |
| L1 Cache | 512 KB | 3.3 MB |
| L2 Cache | 512 KB | 32 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).
| Laptop size | large | no data |
| Bus support | PCIe 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 5.0 x16 |
| Supplementary power connectors | None | no data |
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 | GDDR5 | GDDR7 |
| Maximum RAM amount | 4 GB | 8 GB |
| Memory bus width | 256 Bit | 128 Bit |
| Memory clock speed | no data | 1500 MHz |
| Memory bandwidth | 160.0 GB/s | 384.0 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 | No outputs | Portable Device Dependent |
| Eyefinity | + | - |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| FreeSync | + | - |
| HD3D | + | - |
| PowerTune | + | - |
| DualGraphics | + | - |
| ZeroCore | + | - |
| Switchable graphics | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | DirectX® 12 | 12 Ultimate (12_2) |
| Shader Model | 6.3 | 6.8 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | Not Listed | 3.0 |
| Vulkan | + | 1.4 |
| Mantle | + | - |
| 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.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
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 | 30−35
−317%
| 125
+317%
|
| 1440p | 18−20
−289%
| 70
+289%
|
| 4K | 18−21
−350%
| 81
+350%
|
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 50−55
−306%
|
200−210
+306%
|
| Cyberpunk 2077 | 18−20
−342%
|
80−85
+342%
|
| Resident Evil 4 Remake | 18−20
−433%
|
95−100
+433%
|
Full HD
Medium
| Battlefield 5 | 40−45
−205%
|
120−130
+205%
|
| Counter-Strike 2 | 50−55
−306%
|
200−210
+306%
|
| Cyberpunk 2077 | 18−20
−342%
|
80−85
+342%
|
| Far Cry 5 | 30−33
−290%
|
110−120
+290%
|
| Fortnite | 55−60
−181%
|
160−170
+181%
|
| Forza Horizon 4 | 40−45
−244%
|
140−150
+244%
|
| Forza Horizon 5 | 27−30
−297%
|
110−120
+297%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 30−35
−326%
|
140−150
+326%
|
| Valorant | 90−95
−138%
|
210−220
+138%
|
Full HD
High
| Battlefield 5 | 40−45
−205%
|
120−130
+205%
|
| Counter-Strike 2 | 50−55
−306%
|
200−210
+306%
|
| Counter-Strike: Global Offensive | 140−150
−94.4%
|
270−280
+94.4%
|
| Cyberpunk 2077 | 18−20
−342%
|
80−85
+342%
|
| Dota 2 | 65−70
−277%
|
260−270
+277%
|
| Far Cry 5 | 30−33
−290%
|
110−120
+290%
|
| Fortnite | 55−60
−181%
|
160−170
+181%
|
| Forza Horizon 4 | 40−45
−244%
|
140−150
+244%
|
| Forza Horizon 5 | 27−30
−297%
|
110−120
+297%
|
| Grand Theft Auto V | 35−40
−317%
|
146
+317%
|
| Metro Exodus | 18−20
−353%
|
85−90
+353%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 30−35
−326%
|
140−150
+326%
|
| The Witcher 3: Wild Hunt | 24−27
−425%
|
120−130
+425%
|
| Valorant | 90−95
−138%
|
210−220
+138%
|
Full HD
Ultra
| Battlefield 5 | 40−45
−205%
|
120−130
+205%
|
| Cyberpunk 2077 | 18−20
−342%
|
80−85
+342%
|
| Dota 2 | 65−70
−277%
|
260−270
+277%
|
| Far Cry 5 | 30−33
−290%
|
110−120
+290%
|
| Forza Horizon 4 | 40−45
−244%
|
140−150
+244%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 30−35
−326%
|
140−150
+326%
|
| The Witcher 3: Wild Hunt | 24−27
−425%
|
120−130
+425%
|
| Valorant | 90−95
−285%
|
350−400
+285%
|
Full HD
Epic
| Fortnite | 55−60
−181%
|
160−170
+181%
|
1440p
High
| Counter-Strike 2 | 18−20
−400%
|
90−95
+400%
|
| Counter-Strike: Global Offensive | 70−75
−256%
|
250−260
+256%
|
| Grand Theft Auto V | 12−14
−615%
|
93
+615%
|
| Metro Exodus | 10−11
−430%
|
50−55
+430%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 45−50
−267%
|
180−190
+267%
|
| Valorant | 100−110
−140%
|
250−260
+140%
|
1440p
Ultra
| Battlefield 5 | 21−24
−313%
|
95−100
+313%
|
| Cyberpunk 2077 | 8−9
−425%
|
40−45
+425%
|
| Far Cry 5 | 20−22
−340%
|
85−90
+340%
|
| Forza Horizon 4 | 21−24
−364%
|
100−110
+364%
|
| The Witcher 3: Wild Hunt | 12−14
−415%
|
65−70
+415%
|
1440p
Epic
| Fortnite | 20−22
−375%
|
95−100
+375%
|
4K
High
| Counter-Strike 2 | 4−5
−925%
|
40−45
+925%
|
| Grand Theft Auto V | 20−22
−290%
|
75−80
+290%
|
| Metro Exodus | 5−6
−560%
|
30−35
+560%
|
| The Witcher 3: Wild Hunt | 10−11
−470%
|
55−60
+470%
|
| Valorant | 45−50
−355%
|
220−230
+355%
|
4K
Ultra
| Battlefield 5 | 10−12
−427%
|
55−60
+427%
|
| Counter-Strike 2 | 4−5
−250%
|
14−16
+250%
|
| Cyberpunk 2077 | 3−4
−533%
|
18−20
+533%
|
| Dota 2 | 35−40
−271%
|
130−140
+271%
|
| Far Cry 5 | 9−10
−422%
|
45−50
+422%
|
| Forza Horizon 4 | 16−18
−325%
|
65−70
+325%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 9−10
−422%
|
45−50
+422%
|
4K
Epic
| Fortnite | 9−10
−411%
|
45−50
+411%
|
This is how R9 M390X and RTX PRO 2000 Blackwell Mobile compete in popular games:
- RTX PRO 2000 Blackwell Mobile is 317% faster in 1080p
- RTX PRO 2000 Blackwell Mobile is 289% faster in 1440p
- RTX PRO 2000 Blackwell Mobile is 350% faster in 4K
Here's the range of performance differences observed across popular games:
- in Counter-Strike 2, with 4K resolution and the High Preset, the RTX PRO 2000 Blackwell Mobile is 925% faster.
All in all, in popular games:
- Without exception, RTX PRO 2000 Blackwell Mobile surpassed R9 M390X in all 54 of our tests.
Pros & cons summary
| Performance score | 9.31 | 35.99 |
| Recency | 5 May 2015 | 19 March 2025 |
| Maximum RAM amount | 4 GB | 8 GB |
| Chip lithography | 28 nm | 5 nm |
| Power consumption (TDP) | 100 Watt | 45 Watt |
RTX PRO 2000 Blackwell Mobile has a 287% higher aggregate performance score, an age advantage of 9 years, a 100% higher maximum VRAM amount, a 460% more advanced lithography process, and 122% lower power consumption.
The RTX PRO 2000 Blackwell Mobile is our recommended choice as it beats the Radeon R9 M390X in performance tests.
Be aware that Radeon R9 M390X is a notebook graphics card while RTX PRO 2000 Blackwell Mobile is a mobile workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
