GeForce RTX 5070 Mobile vs Radeon Pro V620
Aggregate performance score
We've compared Radeon Pro V620 with GeForce RTX 5070 Mobile, including specs and performance data.
RTX 5070 Mobile outperforms Pro V620 by a substantial 30% 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 | 132 | 67 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 9.46 | 74.00 |
| Architecture | RDNA 2.0 (2020−2025) | Blackwell 2.0 (2025) |
| GPU code name | Navi 21 | GB206 |
| Market segment | Workstation | Laptop |
| Release date | 4 November 2021 (3 years ago) | April 2025 (recently) |
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 | 4608 | 4608 |
| Core clock speed | 1825 MHz | 907 MHz |
| Boost clock speed | 2200 MHz | 1425 MHz |
| Number of transistors | 26,800 million | 21,900 million |
| Manufacturing process technology | 7 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 50 Watt |
| Texture fill rate | 633.6 | 205.2 |
| Floating-point processing power | 20.28 TFLOPS | 13.13 TFLOPS |
| ROPs | 128 | 48 |
| TMUs | 288 | 144 |
| Tensor Cores | no data | 144 |
| Ray Tracing Cores | 72 | 36 |
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 | no data | medium sized |
| Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Length | 267 mm | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 2x 8-pin | 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 | GDDR6 | GDDR7 |
| Maximum RAM amount | 32 GB | 8 GB |
| Memory bus width | 256 Bit | 128 Bit |
| Memory clock speed | 2000 MHz | 1500 MHz |
| Memory bandwidth | 512.0 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 |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.5 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.4 |
| CUDA | - | 12.0 |
| 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 | 85−90
−34.1%
| 114
+34.1%
|
| 1440p | 50−55
−42%
| 71
+42%
|
| 4K | 27−30
−37%
| 37
+37%
|
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 260−270
+0%
|
260−270
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Sons of the Forest | 100−105
+0%
|
100−105
+0%
|
Full HD
Medium Preset
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Counter-Strike 2 | 222
+0%
|
222
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Far Cry 5 | 150−160
+0%
|
150−160
+0%
|
| Fortnite | 210−220
+0%
|
210−220
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| Forza Horizon 5 | 150−160
+0%
|
150−160
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Sons of the Forest | 100−105
+0%
|
100−105
+0%
|
| Valorant | 270−280
+0%
|
270−280
+0%
|
Full HD
High Preset
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Counter-Strike 2 | 163
+0%
|
163
+0%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Far Cry 5 | 150−160
+0%
|
150−160
+0%
|
| Fortnite | 210−220
+0%
|
210−220
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| Forza Horizon 5 | 150−160
+0%
|
150−160
+0%
|
| Grand Theft Auto V | 141
+0%
|
141
+0%
|
| Metro Exodus | 120−130
+0%
|
120−130
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Sons of the Forest | 100−105
+0%
|
100−105
+0%
|
| The Witcher 3: Wild Hunt | 180−190
+0%
|
180−190
+0%
|
| Valorant | 270−280
+0%
|
270−280
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Far Cry 5 | 150−160
+0%
|
150−160
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Sons of the Forest | 100−105
+0%
|
100−105
+0%
|
| The Witcher 3: Wild Hunt | 105
+0%
|
105
+0%
|
Full HD
Epic Preset
| Fortnite | 210−220
+0%
|
210−220
+0%
|
1440p
High Preset
| Counter-Strike 2 | 115
+0%
|
115
+0%
|
| Counter-Strike: Global Offensive | 300−350
+0%
|
300−350
+0%
|
| Grand Theft Auto V | 108
+0%
|
108
+0%
|
| Metro Exodus | 75−80
+0%
|
75−80
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 120−130
+0%
|
120−130
+0%
|
| Cyberpunk 2077 | 60−65
+0%
|
60−65
+0%
|
| Far Cry 5 | 120−130
+0%
|
120−130
+0%
|
| Forza Horizon 4 | 150−160
+0%
|
150−160
+0%
|
| Sons of the Forest | 75−80
+0%
|
75−80
+0%
|
| The Witcher 3: Wild Hunt | 100−110
+0%
|
100−110
+0%
|
1440p
Epic Preset
| Fortnite | 130−140
+0%
|
130−140
+0%
|
4K
High Preset
| Counter-Strike 2 | 60−65
+0%
|
60−65
+0%
|
| Grand Theft Auto V | 110−120
+0%
|
110−120
+0%
|
| Metro Exodus | 45−50
+0%
|
45−50
+0%
|
| The Witcher 3: Wild Hunt | 80−85
+0%
|
80−85
+0%
|
| Valorant | 280−290
+0%
|
280−290
+0%
|
4K
Ultra Preset
| Battlefield 5 | 80−85
+0%
|
80−85
+0%
|
| Cyberpunk 2077 | 27−30
+0%
|
27−30
+0%
|
| Far Cry 5 | 70−75
+0%
|
70−75
+0%
|
| Forza Horizon 4 | 100−110
+0%
|
100−110
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 75−80
+0%
|
75−80
+0%
|
| Sons of the Forest | 45−50
+0%
|
45−50
+0%
|
4K
Epic Preset
| Fortnite | 70−75
+0%
|
70−75
+0%
|
This is how Pro V620 and RTX 5070 Mobile compete in popular games:
- RTX 5070 Mobile is 34% faster in 1080p
- RTX 5070 Mobile is 42% faster in 1440p
- RTX 5070 Mobile is 37% faster in 4K
All in all, in popular games:
- there's a draw in 59 tests (100%)
Pros & cons summary
| Performance score | 37.30 | 48.64 |
| Recency | 4 November 2021 | on April 2025 |
| Maximum RAM amount | 32 GB | 8 GB |
| Chip lithography | 7 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 50 Watt |
Pro V620 has a 300% higher maximum VRAM amount.
RTX 5070 Mobile, on the other hand, has a 30.4% higher aggregate performance score, an age advantage of 3 years, a 40% more advanced lithography process, and 500% lower power consumption.
The GeForce RTX 5070 Mobile is our recommended choice as it beats the Radeon Pro V620 in performance tests.
Be aware that Radeon Pro V620 is a workstation graphics card while GeForce RTX 5070 Mobile is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
