GeForce RTX 4070 Ti SUPER vs Radeon 625
Aggregate performance score
We've compared Radeon 625 with GeForce RTX 4070 Ti SUPER, including specs and performance data.
RTX 4070 Ti SUPER outperforms 625 by a whopping 2865% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 809 | 9 |
| Place by popularity | not in top-100 | 84 |
| Cost-effectiveness evaluation | no data | 49.14 |
| Power efficiency | 3.82 | 19.88 |
| Architecture | GCN 3.0 (2014−2019) | Ada Lovelace (2022−2024) |
| GPU code name | Polaris 24 | AD103 |
| Market segment | Laptop | Desktop |
| Release date | 13 May 2019 (5 years ago) | 8 January 2024 (1 year ago) |
| Launch price (MSRP) | no data | $799 |
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 | 384 | 8448 |
| Core clock speed | 730 MHz | 2340 MHz |
| Boost clock speed | 1024 MHz | 2610 MHz |
| Number of transistors | 1,550 million | 45,900 million |
| Manufacturing process technology | 28 nm | 5 nm |
| Power consumption (TDP) | 50 Watt | 285 Watt |
| Texture fill rate | 24.58 | 689.0 |
| Floating-point processing power | 0.7864 TFLOPS | 44.1 TFLOPS |
| ROPs | 8 | 96 |
| TMUs | 24 | 264 |
| Tensor Cores | no data | 264 |
| Ray Tracing Cores | no data | 66 |
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 3.0 x8 | PCIe 4.0 x16 |
| Length | no data | 310 mm |
| Width | no data | 3-slot |
| Supplementary power connectors | None | 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 | DDR3 | GDDR6X |
| Maximum RAM amount | 2 GB | 16 GB |
| Memory bus width | 64 Bit | 256 Bit |
| Memory clock speed | 900 MHz | 1313 MHz |
| Memory bandwidth | 14.4 GB/s | 672.3 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 | No outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
| Shader Model | 6.3 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2.131 | 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
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 | 7−8
−3071%
| 222
+3071%
|
| 1440p | 4−5
−3550%
| 146
+3550%
|
| 4K | 3−4
−2867%
| 89
+2867%
|
Cost per frame, $
| 1080p | no data | 3.60 |
| 1440p | no data | 5.47 |
| 4K | no data | 8.98 |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 7−8
−3171%
|
220−230
+3171%
|
| Counter-Strike 2 | 6−7
−5400%
|
300−350
+5400%
|
| Cyberpunk 2077 | 6−7
−3183%
|
197
+3183%
|
Full HD
Medium Preset
| Atomic Heart | 7−8
−3171%
|
220−230
+3171%
|
| Battlefield 5 | 8−9
−2313%
|
190−200
+2313%
|
| Counter-Strike 2 | 6−7
−5400%
|
300−350
+5400%
|
| Cyberpunk 2077 | 6−7
−3167%
|
196
+3167%
|
| Far Cry 5 | 5−6
−3960%
|
203
+3960%
|
| Fortnite | 12−14
−2223%
|
300−350
+2223%
|
| Forza Horizon 4 | 12−14
−2338%
|
300−350
+2338%
|
| Forza Horizon 5 | 4−5
−5300%
|
210−220
+5300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1262%
|
170−180
+1262%
|
| Valorant | 40−45
−973%
|
450−500
+973%
|
Full HD
High Preset
| Atomic Heart | 7−8
−3171%
|
220−230
+3171%
|
| Battlefield 5 | 8−9
−2313%
|
190−200
+2313%
|
| Counter-Strike 2 | 6−7
−5400%
|
300−350
+5400%
|
| Counter-Strike: Global Offensive | 50−55
−456%
|
270−280
+456%
|
| Cyberpunk 2077 | 6−7
−2767%
|
172
+2767%
|
| Dota 2 | 24−27
−2785%
|
750−800
+2785%
|
| Far Cry 5 | 5−6
−3840%
|
197
+3840%
|
| Fortnite | 12−14
−2223%
|
300−350
+2223%
|
| Forza Horizon 4 | 12−14
−2338%
|
300−350
+2338%
|
| Forza Horizon 5 | 4−5
−5300%
|
210−220
+5300%
|
| Grand Theft Auto V | 7−8
−2386%
|
174
+2386%
|
| Metro Exodus | 4−5
−4800%
|
196
+4800%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1262%
|
170−180
+1262%
|
| The Witcher 3: Wild Hunt | 8−9
−5275%
|
430
+5275%
|
| Valorant | 40−45
−973%
|
450−500
+973%
|
Full HD
Ultra Preset
| Battlefield 5 | 8−9
−2313%
|
190−200
+2313%
|
| Cyberpunk 2077 | 6−7
−2533%
|
158
+2533%
|
| Dota 2 | 24−27
−2785%
|
750−800
+2785%
|
| Far Cry 5 | 5−6
−3660%
|
188
+3660%
|
| Forza Horizon 4 | 12−14
−2338%
|
300−350
+2338%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1262%
|
170−180
+1262%
|
| The Witcher 3: Wild Hunt | 8−9
−2525%
|
210
+2525%
|
| Valorant | 40−45
−973%
|
450−500
+973%
|
Full HD
Epic Preset
| Fortnite | 12−14
−2223%
|
300−350
+2223%
|
1440p
High Preset
| Counter-Strike 2 | 3−4
−8100%
|
240−250
+8100%
|
| Counter-Strike: Global Offensive | 18−20
−2616%
|
500−550
+2616%
|
| Grand Theft Auto V | 1−2
−15400%
|
155
+15400%
|
| Metro Exodus | 0−1 | 131 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 21−24
−661%
|
170−180
+661%
|
| Valorant | 24−27
−1921%
|
450−500
+1921%
|
1440p
Ultra Preset
| Cyberpunk 2077 | 2−3
−5100%
|
104
+5100%
|
| Far Cry 5 | 4−5
−4575%
|
187
+4575%
|
| Forza Horizon 4 | 6−7
−4600%
|
280−290
+4600%
|
| The Witcher 3: Wild Hunt | 4−5
−3875%
|
159
+3875%
|
1440p
Epic Preset
| Fortnite | 5−6
−2920%
|
150−160
+2920%
|
4K
High Preset
| Atomic Heart | 2−3
−3800%
|
75−80
+3800%
|
| Grand Theft Auto V | 16−18
−1038%
|
182
+1038%
|
| Valorant | 12−14
−2454%
|
300−350
+2454%
|
4K
Ultra Preset
| Cyberpunk 2077 | 1−2
−4900%
|
50
+4900%
|
| Dota 2 | 7−8
−2757%
|
200−210
+2757%
|
| Far Cry 5 | 3−4
−3867%
|
119
+3867%
|
| Forza Horizon 4 | 2−3
−12350%
|
240−250
+12350%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−3100%
|
95−100
+3100%
|
4K
Epic Preset
| Fortnite | 3−4
−2533%
|
75−80
+2533%
|
1440p
Ultra Preset
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
4K
High Preset
| Counter-Strike 2 | 36
+0%
|
36
+0%
|
| Metro Exodus | 84
+0%
|
84
+0%
|
| The Witcher 3: Wild Hunt | 180−190
+0%
|
180−190
+0%
|
4K
Ultra Preset
| Battlefield 5 | 130−140
+0%
|
130−140
+0%
|
| Counter-Strike 2 | 110−120
+0%
|
110−120
+0%
|
This is how Radeon 625 and RTX 4070 Ti SUPER compete in popular games:
- RTX 4070 Ti SUPER is 3071% faster in 1080p
- RTX 4070 Ti SUPER is 3550% faster in 1440p
- RTX 4070 Ti SUPER is 2867% faster in 4K
Here's the range of performance differences observed across popular games:
- in Grand Theft Auto V, with 1440p resolution and the High Preset, the RTX 4070 Ti SUPER is 15400% faster.
All in all, in popular games:
- RTX 4070 Ti SUPER is ahead in 53 tests (90%)
- there's a draw in 6 tests (10%)
Pros & cons summary
| Performance score | 2.40 | 71.17 |
| Recency | 13 May 2019 | 8 January 2024 |
| Maximum RAM amount | 2 GB | 16 GB |
| Chip lithography | 28 nm | 5 nm |
| Power consumption (TDP) | 50 Watt | 285 Watt |
Radeon 625 has 470% lower power consumption.
RTX 4070 Ti SUPER, on the other hand, has a 2865.4% higher aggregate performance score, an age advantage of 4 years, a 700% higher maximum VRAM amount, and a 460% more advanced lithography process.
The GeForce RTX 4070 Ti SUPER is our recommended choice as it beats the Radeon 625 in performance tests.
Be aware that Radeon 625 is a notebook card while GeForce RTX 4070 Ti SUPER 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.
