GeForce RTX 5070 vs RTX 4070 Mobile
Aggregate performance score
We've compared GeForce RTX 4070 Mobile with GeForce RTX 5070, including specs and performance data.
RTX 5070 outperforms RTX 4070 Mobile by an impressive 62% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 64 | 10 |
| Place by popularity | not in top-100 | 64 |
| Power efficiency | 30.24 | 22.59 |
| Architecture | Ada Lovelace (2022−2024) | Blackwell 2.0 (2025) |
| GPU code name | AD106 | GB205 |
| Market segment | Laptop | Desktop |
| Release date | 3 January 2023 (2 years ago) | March 2025 (recently) |
| Launch price (MSRP) | no data | $549 |
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 | 6144 |
| Core clock speed | 1395 MHz | 2325 MHz |
| Boost clock speed | 1695 MHz | 2512 MHz |
| Number of transistors | no data | 31,100 million |
| Manufacturing process technology | 4 nm | 5 nm |
| Power consumption (TDP) | 115 Watt | 250 Watt |
| Texture fill rate | 244.1 | 482.3 |
| Floating-point processing power | 15.62 TFLOPS | 30.87 TFLOPS |
| ROPs | 48 | 80 |
| TMUs | 144 | 192 |
| Tensor Cores | 144 | 192 |
| Ray Tracing Cores | 36 | 48 |
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 |
| Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 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 | GDDR7 |
| Maximum RAM amount | 8 GB | 12 GB |
| Memory bus width | 128 Bit | 192 Bit |
| Memory clock speed | 2000 MHz | 1750 MHz |
| Memory bandwidth | 256.0 GB/s | 672.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | + | + |
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 | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |
| HDMI | - | + |
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 | 6.7 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.4 |
| CUDA | 8.9 | 10.1 |
| 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 | 128
−56.3%
| 200−210
+56.3%
|
| 1440p | 75
−60%
| 120−130
+60%
|
| 4K | 46
−52.2%
| 70−75
+52.2%
|
Cost per frame, $
| 1080p | no data | 2.75 |
| 1440p | no data | 4.58 |
| 4K | no data | 7.84 |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 188
−21.8%
|
220−230
+21.8%
|
| Counter-Strike 2 | 250−260
−28.9%
|
300−350
+28.9%
|
| Cyberpunk 2077 | 135
−45.2%
|
190−200
+45.2%
|
Full HD
Medium Preset
| Atomic Heart | 140
−63.6%
|
220−230
+63.6%
|
| Battlefield 5 | 140−150
−31.3%
|
190−200
+31.3%
|
| Counter-Strike 2 | 172
−91.9%
|
300−350
+91.9%
|
| Cyberpunk 2077 | 115
−70.4%
|
190−200
+70.4%
|
| Far Cry 5 | 139
−38.8%
|
190−200
+38.8%
|
| Fortnite | 200−210
−49.5%
|
300−350
+49.5%
|
| Forza Horizon 4 | 180−190
−76.1%
|
300−350
+76.1%
|
| Forza Horizon 5 | 216
+0%
|
210−220
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
−2.9%
|
170−180
+2.9%
|
| Valorant | 260−270
−81.2%
|
450−500
+81.2%
|
Full HD
High Preset
| Atomic Heart | 95
−141%
|
220−230
+141%
|
| Battlefield 5 | 140−150
−31.3%
|
190−200
+31.3%
|
| Counter-Strike 2 | 146
−126%
|
300−350
+126%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 97
−102%
|
190−200
+102%
|
| Dota 2 | 178
−57.3%
|
280−290
+57.3%
|
| Far Cry 5 | 133
−45.1%
|
190−200
+45.1%
|
| Fortnite | 200−210
−49.5%
|
300−350
+49.5%
|
| Forza Horizon 4 | 180−190
−76.1%
|
300−350
+76.1%
|
| Forza Horizon 5 | 195
−10.8%
|
210−220
+10.8%
|
| Grand Theft Auto V | 144
−20.8%
|
170−180
+20.8%
|
| Metro Exodus | 111
−76.6%
|
190−200
+76.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
−2.9%
|
170−180
+2.9%
|
| The Witcher 3: Wild Hunt | 229
−48%
|
300−350
+48%
|
| Valorant | 260−270
−81.2%
|
450−500
+81.2%
|
Full HD
Ultra Preset
| Battlefield 5 | 140−150
−31.3%
|
190−200
+31.3%
|
| Cyberpunk 2077 | 87
−125%
|
190−200
+125%
|
| Dota 2 | 167
−61.7%
|
270−280
+61.7%
|
| Far Cry 5 | 123
−56.9%
|
190−200
+56.9%
|
| Forza Horizon 4 | 180−190
−76.1%
|
300−350
+76.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
−2.9%
|
170−180
+2.9%
|
| The Witcher 3: Wild Hunt | 116
−192%
|
300−350
+192%
|
| Valorant | 260−270
−81.2%
|
450−500
+81.2%
|
Full HD
Epic Preset
| Fortnite | 200−210
−49.5%
|
300−350
+49.5%
|
1440p
High Preset
| Counter-Strike 2 | 94
−163%
|
240−250
+163%
|
| Counter-Strike: Global Offensive | 300−350
−56.8%
|
500−550
+56.8%
|
| Grand Theft Auto V | 90
−73.3%
|
150−160
+73.3%
|
| Metro Exodus | 69
−103%
|
140−150
+103%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 290−300
−66.7%
|
450−500
+66.7%
|
1440p
Ultra Preset
| Battlefield 5 | 110−120
−69%
|
190−200
+69%
|
| Cyberpunk 2077 | 54
−119%
|
110−120
+119%
|
| Far Cry 5 | 112
−60.7%
|
180−190
+60.7%
|
| Forza Horizon 4 | 140−150
−99.3%
|
280−290
+99.3%
|
| The Witcher 3: Wild Hunt | 89
−125%
|
200−210
+125%
|
1440p
Epic Preset
| Fortnite | 120−130
−17.1%
|
150−160
+17.1%
|
4K
High Preset
| Atomic Heart | 35−40
−100%
|
75−80
+100%
|
| Counter-Strike 2 | 43
−160%
|
110−120
+160%
|
| Grand Theft Auto V | 90
−102%
|
180−190
+102%
|
| Metro Exodus | 44
−120%
|
95−100
+120%
|
| The Witcher 3: Wild Hunt | 71
−168%
|
190−200
+168%
|
| Valorant | 280−290
−18.6%
|
300−350
+18.6%
|
4K
Ultra Preset
| Battlefield 5 | 75−80
−76.6%
|
130−140
+76.6%
|
| Counter-Strike 2 | 55−60
−93.1%
|
110−120
+93.1%
|
| Cyberpunk 2077 | 24
−142%
|
55−60
+142%
|
| Dota 2 | 146
−57.5%
|
230−240
+57.5%
|
| Far Cry 5 | 61
−113%
|
130−140
+113%
|
| Forza Horizon 4 | 95−100
−157%
|
240−250
+157%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 70−75
−31.5%
|
95−100
+31.5%
|
4K
Epic Preset
| Fortnite | 65−70
−19.7%
|
75−80
+19.7%
|
This is how RTX 4070 Mobile and RTX 5070 compete in popular games:
- RTX 5070 is 56% faster in 1080p
- RTX 5070 is 60% faster in 1440p
- RTX 5070 is 52% faster in 4K
Here's the range of performance differences observed across popular games:
- in The Witcher 3: Wild Hunt, with 1080p resolution and the Ultra Preset, the RTX 5070 is 192% faster.
All in all, in popular games:
- RTX 5070 is ahead in 57 tests (95%)
- there's a draw in 3 tests (5%)
Pros & cons summary
| Performance score | 43.70 | 70.96 |
| Maximum RAM amount | 8 GB | 12 GB |
| Chip lithography | 4 nm | 5 nm |
| Power consumption (TDP) | 115 Watt | 250 Watt |
RTX 4070 Mobile has a 25% more advanced lithography process, and 117.4% lower power consumption.
RTX 5070, on the other hand, has a 62.4% higher aggregate performance score, and a 50% higher maximum VRAM amount.
The GeForce RTX 5070 is our recommended choice as it beats the GeForce RTX 4070 Mobile in performance tests.
Be aware that GeForce RTX 4070 Mobile is a notebook card while GeForce RTX 5070 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.
