GeForce RTX 5070 Ti vs Radeon 660M
Aggregate performance score
We've compared Radeon 660M with GeForce RTX 5070 Ti, including specs and performance data.
RTX 5070 Ti outperforms 660M by a whopping 874% 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 | 511 | 7 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 54.90 |
| Power efficiency | 14.79 | 19.21 |
| Architecture | RDNA 2.0 (2020−2024) | Blackwell 2.0 (2025) |
| GPU code name | Rembrandt+ | GB203 |
| Market segment | Laptop | Desktop |
| Release date | 3 January 2023 (2 years ago) | 20 February 2025 (less than a year ago) |
| Launch price (MSRP) | no data | $749 |
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 | 8960 |
| Core clock speed | 1500 MHz | 2295 MHz |
| Boost clock speed | 1900 MHz | 2452 MHz |
| Number of transistors | 13,100 million | 45,600 million |
| Manufacturing process technology | 6 nm | 5 nm |
| Power consumption (TDP) | 40 Watt | 300 Watt |
| Texture fill rate | 45.60 | 686.6 |
| Floating-point processing power | 1.459 TFLOPS | 43.94 TFLOPS |
| ROPs | 16 | 96 |
| TMUs | 24 | 280 |
| Tensor Cores | no data | 280 |
| Ray Tracing Cores | 6 | 70 |
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 4.0 x8 | PCIe 5.0 x16 |
| Length | no data | 304 mm |
| Width | no data | 2-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 | System Shared | GDDR7 |
| Maximum RAM amount | System Shared | 16 GB |
| Memory bus width | System Shared | 256 Bit |
| Memory clock speed | System Shared | 1750 MHz |
| Memory bandwidth | no data | 896.0 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 | 2.0 | 3.0 |
| Vulkan | 1.3 | 1.4 |
| CUDA | - | 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 | 25
−508%
| 152
+508%
|
| 1440p | 10−12
−1060%
| 116
+1060%
|
| 4K | 8−9
−938%
| 83
+938%
|
Cost per frame, $
| 1080p | no data | 4.93 |
| 1440p | no data | 6.46 |
| 4K | no data | 9.02 |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 40−45
−688%
|
300−350
+688%
|
| Cyberpunk 2077 | 24
−738%
|
200−210
+738%
|
| Hogwarts Legacy | 23
−630%
|
160−170
+630%
|
Full HD
Medium Preset
| Battlefield 5 | 35−40
−444%
|
190−200
+444%
|
| Counter-Strike 2 | 40−45
−688%
|
300−350
+688%
|
| Cyberpunk 2077 | 20
−905%
|
200−210
+905%
|
| Far Cry 5 | 30
−573%
|
200−210
+573%
|
| Fortnite | 45−50
−516%
|
300−350
+516%
|
| Forza Horizon 4 | 35−40
−808%
|
300−350
+808%
|
| Forza Horizon 5 | 39
−464%
|
220−230
+464%
|
| Hogwarts Legacy | 17
−888%
|
160−170
+888%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
−507%
|
170−180
+507%
|
| Valorant | 80−85
−502%
|
450−500
+502%
|
Full HD
High Preset
| Battlefield 5 | 35−40
−444%
|
190−200
+444%
|
| Counter-Strike 2 | 40−45
−688%
|
300−350
+688%
|
| Counter-Strike: Global Offensive | 120−130
−119%
|
270−280
+119%
|
| Cyberpunk 2077 | 14
−1336%
|
200−210
+1336%
|
| Dota 2 | 56
−793%
|
500−550
+793%
|
| Far Cry 5 | 26
−677%
|
200−210
+677%
|
| Fortnite | 45−50
−516%
|
300−350
+516%
|
| Forza Horizon 4 | 35−40
−808%
|
300−350
+808%
|
| Forza Horizon 5 | 32
−588%
|
220−230
+588%
|
| Grand Theft Auto V | 24
−625%
|
170−180
+625%
|
| Hogwarts Legacy | 13
−1192%
|
160−170
+1192%
|
| Metro Exodus | 15
−1233%
|
200−210
+1233%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
−507%
|
170−180
+507%
|
| The Witcher 3: Wild Hunt | 25
−1304%
|
350−400
+1304%
|
| Valorant | 80−85
−502%
|
450−500
+502%
|
Full HD
Ultra Preset
| Battlefield 5 | 35−40
−444%
|
190−200
+444%
|
| Cyberpunk 2077 | 16−18
−1156%
|
200−210
+1156%
|
| Dota 2 | 48
−838%
|
450−500
+838%
|
| Far Cry 5 | 25
−708%
|
200−210
+708%
|
| Forza Horizon 4 | 35−40
−808%
|
300−350
+808%
|
| Hogwarts Legacy | 10
−1580%
|
160−170
+1580%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
−507%
|
170−180
+507%
|
| The Witcher 3: Wild Hunt | 15
−1500%
|
240
+1500%
|
| Valorant | 80−85
−502%
|
450−500
+502%
|
Full HD
Epic Preset
| Fortnite | 45−50
−516%
|
300−350
+516%
|
1440p
High Preset
| Counter-Strike 2 | 14−16
−1714%
|
250−260
+1714%
|
| Counter-Strike: Global Offensive | 60−65
−732%
|
500−550
+732%
|
| Grand Theft Auto V | 10−12
−1345%
|
150−160
+1345%
|
| Metro Exodus | 9−10
−1500%
|
140−150
+1500%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
−327%
|
170−180
+327%
|
| Valorant | 90−95
−427%
|
450−500
+427%
|
1440p
Ultra Preset
| Battlefield 5 | 18−20
−989%
|
190−200
+989%
|
| Cyberpunk 2077 | 7−8
−1643%
|
120−130
+1643%
|
| Far Cry 5 | 16−18
−1006%
|
180−190
+1006%
|
| Forza Horizon 4 | 18−20
−1437%
|
290−300
+1437%
|
| Hogwarts Legacy | 9−10
−1156%
|
110−120
+1156%
|
| The Witcher 3: Wild Hunt | 10−12
−1709%
|
199
+1709%
|
1440p
Epic Preset
| Fortnite | 16−18
−788%
|
150−160
+788%
|
4K
High Preset
| Counter-Strike 2 | 1−2
−11500%
|
110−120
+11500%
|
| Grand Theft Auto V | 18−20
−868%
|
180−190
+868%
|
| Hogwarts Legacy | 3−4
−2167%
|
65−70
+2167%
|
| Metro Exodus | 3−4
−3233%
|
100−105
+3233%
|
| The Witcher 3: Wild Hunt | 8−9
−2188%
|
183
+2188%
|
| Valorant | 40−45
−688%
|
300−350
+688%
|
4K
Ultra Preset
| Battlefield 5 | 9−10
−1411%
|
130−140
+1411%
|
| Counter-Strike 2 | 1−2
−11500%
|
110−120
+11500%
|
| Cyberpunk 2077 | 3−4
−1900%
|
60−65
+1900%
|
| Dota 2 | 30−33
−867%
|
290−300
+867%
|
| Far Cry 5 | 9−10
−1422%
|
130−140
+1422%
|
| Forza Horizon 4 | 12−14
−1923%
|
260−270
+1923%
|
| Hogwarts Legacy | 3−4
−2167%
|
65−70
+2167%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 8−9
−1100%
|
95−100
+1100%
|
4K
Epic Preset
| Fortnite | 8−9
−888%
|
75−80
+888%
|
This is how Radeon 660M and RTX 5070 Ti compete in popular games:
- RTX 5070 Ti is 508% faster in 1080p
- RTX 5070 Ti is 1060% faster in 1440p
- RTX 5070 Ti is 938% 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 5070 Ti is 11500% faster.
All in all, in popular games:
- Without exception, RTX 5070 Ti surpassed Radeon 660M in all 63 of our tests.
Pros & cons summary
| Performance score | 8.36 | 81.45 |
| Recency | 3 January 2023 | 20 February 2025 |
| Chip lithography | 6 nm | 5 nm |
| Power consumption (TDP) | 40 Watt | 300 Watt |
Radeon 660M has 650% lower power consumption.
RTX 5070 Ti, on the other hand, has a 874.3% higher aggregate performance score, an age advantage of 2 years, and a 20% more advanced lithography process.
The GeForce RTX 5070 Ti is our recommended choice as it beats the Radeon 660M in performance tests.
Be aware that Radeon 660M is a notebook card while GeForce RTX 5070 Ti 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.
