Radeon RX 9070 XT vs GeForce RTX 4090 Mobile
Aggregate performance score
We've compared GeForce RTX 4090 Mobile with Radeon RX 9070 XT, including specs and performance data.
RTX 4090 Mobile outperforms RX 9070 XT by a minimal 3% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 24 | 30 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 60.02 |
| Power efficiency | 40.69 | 15.62 |
| Architecture | Ada Lovelace (2022−2024) | RDNA 4.0 (2025) |
| GPU code name | AD103 | Navi 48 |
| Market segment | Laptop | Desktop |
| Release date | 3 January 2023 (2 years ago) | 6 March 2025 (recently) |
| Launch price (MSRP) | no data | $599 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices 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. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 9728 | 4096 |
| Core clock speed | 1335 MHz | 1660 MHz |
| Boost clock speed | 1695 MHz | 2970 MHz |
| Number of transistors | 45,900 million | 53,900 million |
| Manufacturing process technology | 4 nm | 5 nm |
| Power consumption (TDP) | 120 Watt | 304 Watt |
| Texture fill rate | 515.3 | 760.3 |
| Floating-point processing power | 32.98 TFLOPS | 48.66 TFLOPS |
| ROPs | 112 | 128 |
| TMUs | 304 | 256 |
| Tensor Cores | 304 | 128 |
| Ray Tracing Cores | 76 | 64 |
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 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 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 | GDDR6 | GDDR6 |
| Maximum RAM amount | 16 GB | 16 GB |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 2250 MHz | 2518 MHz |
| Memory bandwidth | 576.0 GB/s | 644.6 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 2.1a |
| 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 | 2.2 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.9 | - |
| 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
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 | 173
+8.1%
| 160−170
−8.1%
|
| 1440p | 133
+10.8%
| 120−130
−10.8%
|
| 4K | 81
+8%
| 75−80
−8%
|
Cost per frame, $
| 1080p | no data | 3.74 |
| 1440p | no data | 4.99 |
| 4K | no data | 7.99 |
FPS performance in popular games
- Full HD
Low Preset - Full HD
Medium Preset - Full HD
High Preset - Full HD
Ultra Preset - Full HD
Epic Preset - 1440p
High Preset - 1440p
Ultra Preset - 1440p
Epic Preset - 4K
High Preset - 4K
Ultra Preset - 4K
Epic Preset
| Atomic Heart | 211
+5.5%
|
200−210
−5.5%
|
| Counter-Strike 2 | 300−350
+1%
|
300−350
−1%
|
| Cyberpunk 2077 | 147
−10.2%
|
160−170
+10.2%
|
| Atomic Heart | 174
−14.9%
|
200−210
+14.9%
|
| Battlefield 5 | 170−180
+1.1%
|
170−180
−1.1%
|
| Counter-Strike 2 | 240
−30.4%
|
300−350
+30.4%
|
| Cyberpunk 2077 | 142
−14.1%
|
160−170
+14.1%
|
| Far Cry 5 | 173
−0.6%
|
170−180
+0.6%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 260−270
+3.1%
|
250−260
−3.1%
|
| Forza Horizon 5 | 181
−3.3%
|
180−190
+3.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 350−400
+3.6%
|
350−400
−3.6%
|
| Atomic Heart | 167
−19.8%
|
200−210
+19.8%
|
| Battlefield 5 | 170−180
+1.1%
|
170−180
−1.1%
|
| Counter-Strike 2 | 214
−46.3%
|
300−350
+46.3%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 133
−21.8%
|
160−170
+21.8%
|
| Dota 2 | 199
+4.7%
|
190−200
−4.7%
|
| Far Cry 5 | 167
−4.2%
|
170−180
+4.2%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Forza Horizon 4 | 260−270
+3.1%
|
250−260
−3.1%
|
| Forza Horizon 5 | 174
−7.5%
|
180−190
+7.5%
|
| Grand Theft Auto V | 162
−3.1%
|
160−170
+3.1%
|
| Metro Exodus | 156
−4.5%
|
160−170
+4.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 394
+46.5%
|
260−270
−46.5%
|
| Valorant | 350−400
+3.6%
|
350−400
−3.6%
|
| Battlefield 5 | 170−180
+1.1%
|
170−180
−1.1%
|
| Cyberpunk 2077 | 128
−26.6%
|
160−170
+26.6%
|
| Dota 2 | 187
+3.9%
|
180−190
−3.9%
|
| Far Cry 5 | 158
−10.1%
|
170−180
+10.1%
|
| Forza Horizon 4 | 260−270
+3.1%
|
250−260
−3.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 204
−31.9%
|
260−270
+31.9%
|
| Valorant | 350−400
+3.6%
|
350−400
−3.6%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Counter-Strike 2 | 173
−13.3%
|
190−200
+13.3%
|
| Counter-Strike: Global Offensive | 516
+3.8%
|
450−500
−3.8%
|
| Grand Theft Auto V | 138
+2.2%
|
130−140
−2.2%
|
| Metro Exodus | 117
+7.3%
|
100−110
−7.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 485
+10%
|
400−450
−10%
|
| Battlefield 5 | 160−170
+3.7%
|
160−170
−3.7%
|
| Cyberpunk 2077 | 95
+3.3%
|
90−95
−3.3%
|
| Far Cry 5 | 151
−2.6%
|
150−160
+2.6%
|
| Forza Horizon 4 | 220−230
+4.1%
|
210−220
−4.1%
|
| The Witcher 3: Wild Hunt | 164
+9.3%
|
150−160
−9.3%
|
| Fortnite | 150−160
+0%
|
150−160
+0%
|
| Atomic Heart | 60−65
+3.4%
|
55−60
−3.4%
|
| Counter-Strike 2 | 88
+0%
|
85−90
+0%
|
| Counter-Strike: Global Offensive | 314
+4.7%
|
300−310
−4.7%
|
| Grand Theft Auto V | 172
+9.6%
|
150−160
−9.6%
|
| Metro Exodus | 82
+17.1%
|
70−75
−17.1%
|
| The Witcher 3: Wild Hunt | 150
+13.6%
|
130−140
−13.6%
|
| Valorant | 300−350
+0.3%
|
300−350
−0.3%
|
| Battlefield 5 | 120−130
+4.2%
|
110−120
−4.2%
|
| Counter-Strike 2 | 90−95
+3.4%
|
85−90
−3.4%
|
| Cyberpunk 2077 | 48
+9.1%
|
40−45
−9.1%
|
| Dota 2 | 179
+5.3%
|
170−180
−5.3%
|
| Far Cry 5 | 107
+4.9%
|
100−110
−4.9%
|
| Forza Horizon 4 | 180−190
+5.9%
|
170−180
−5.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+0%
|
95−100
+0%
|
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how RTX 4090 Mobile and RX 9070 XT compete in popular games:
- RTX 4090 Mobile is 8% faster in 1080p
- RTX 4090 Mobile is 11% faster in 1440p
- RTX 4090 Mobile is 8% 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 High Preset, the RTX 4090 Mobile is 46% faster.
- in Counter-Strike 2, with 1080p resolution and the High Preset, the RX 9070 XT is 46% faster.
All in all, in popular games:
- RTX 4090 Mobile is ahead in 30 tests (50%)
- RX 9070 XT is ahead in 18 tests (30%)
- there's a draw in 12 tests (20%)
Pros & cons summary
| Performance score | 61.46 | 59.75 |
| Recency | 3 January 2023 | 6 March 2025 |
| Chip lithography | 4 nm | 5 nm |
| Power consumption (TDP) | 120 Watt | 304 Watt |
RTX 4090 Mobile has a 2.9% higher aggregate performance score, a 25% more advanced lithography process, and 153.3% lower power consumption.
RX 9070 XT, on the other hand, has an age advantage of 2 years.
Given the minimal performance differences, no clear winner can be declared between GeForce RTX 4090 Mobile and Radeon RX 9070 XT.
Be aware that GeForce RTX 4090 Mobile is a notebook card while Radeon RX 9070 XT 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.
