Radeon 660M vs Quadro RTX 4000
Aggregate performance score
We've compared Quadro RTX 4000 with Radeon 660M, including specs and performance data.
RTX 4000 outperforms 660M by a whopping 375% 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 | 162 | 594 |
| Place by popularity | not in top-100 | 69 |
| Cost-effectiveness evaluation | 10.82 | no data |
| Power efficiency | 17.28 | 14.55 |
| Architecture | Turing (2018−2022) | RDNA 2.0 (2020−2025) |
| GPU code name | TU104 | Rembrandt+ |
| Market segment | Workstation | Laptop |
| Release date | 13 November 2018 (7 years ago) | 3 January 2023 (3 years ago) |
| Launch price (MSRP) | $899 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Currently popular graphics cards are shown 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. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 2304 | 384 |
| Core clock speed | 1005 MHz | 1500 MHz |
| Boost clock speed | 1545 MHz | 1900 MHz |
| Number of transistors | 13,600 million | 13,100 million |
| Manufacturing process technology | 12 nm | 6 nm |
| Power consumption (TDP) | 160 Watt | 40 Watt |
| Texture fill rate | 222.5 | 45.60 |
| Floating-point processing power | 7.119 TFLOPS | 1.459 TFLOPS |
| ROPs | 64 | 16 |
| TMUs | 144 | 24 |
| Tensor Cores | 288 | no data |
| Ray Tracing Cores | 36 | 6 |
| L0 Cache | no data | 96 KB |
| L1 Cache | 2.3 MB | 128 KB |
| L2 Cache | 4 MB | 2 MB |
| L3 Cache | no data | 8 MB |
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 x16 | PCIe 4.0 x8 |
| Length | 241 mm | no data |
| Width | 1-slot | no data |
| Supplementary power connectors | 1x 8-pin | None |
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 | System Shared |
| Maximum RAM amount | 8 GB | System Shared |
| Memory bus width | 256 Bit | System Shared |
| Memory clock speed | 1625 MHz | System Shared |
| Memory bandwidth | 416.0 GB/s | no data |
| Shared memory | - | + |
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 | 3x DisplayPort 1.4a, 1x USB Type-C | Portable Device Dependent |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.8 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 7.5 | - |
| DLSS | + | - |
Synthetic benchmarks
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 | 100−110 | 23
−77%
|
| 4K | 60−65
+362%
| 13 |
Cost per frame, $
| 1080p | 8.99 | no data |
| 4K | 14.98 | no data |
FPS performance in popular games
Full HD
Low
| Atomic Heart | 29 | 29 |
| Counter-Strike 2 | 78 | 78 |
| Cyberpunk 2077 | 24 | 24 |
Full HD
Medium
| Atomic Heart | 23 | 23 |
| Battlefield 5 | 30−35 | 30−35 |
| Counter-Strike 2 | 57 | 57 |
| Cyberpunk 2077 | 20 | 20 |
| Far Cry 5 | 30 | 30 |
| Fortnite | 45−50 | 45−50 |
| Forza Horizon 4 | 30−35 | 30−35 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30 | 27−30 |
| Valorant | 75−80 | 75−80 |
Full HD
High
| Atomic Heart | 13 | 13 |
| Battlefield 5 | 30−35 | 30−35 |
| Counter-Strike 2 | 23 | 23 |
| Counter-Strike: Global Offensive | 120−130 | 120−130 |
| Cyberpunk 2077 | 14 | 14 |
| Dota 2 | 56 | 56 |
| Far Cry 5 | 26 | 26 |
| Far Cry 6 | 21 | 21 |
| Fortnite | 45−50 | 45−50 |
| Forza Horizon 4 | 30−35 | 30−35 |
| Grand Theft Auto V | 25 | 25 |
| Metro Exodus | 15 | 15 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30 | 27−30 |
| The Witcher 3: Wild Hunt | 26 | 26 |
| Valorant | 75−80 | 75−80 |
Full HD
Ultra
| Battlefield 5 | 30−35 | 30−35 |
| Cyberpunk 2077 | 14−16 | 14−16 |
| Dota 2 | 48 | 48 |
| Far Cry 5 | 25 | 25 |
| Forza Horizon 4 | 30−35 | 30−35 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30 | 27−30 |
| The Witcher 3: Wild Hunt | 15 | 15 |
| Valorant | 75−80 | 75−80 |
Full HD
Epic
| Fortnite | 45−50 | 45−50 |
1440p
High
| Counter-Strike 2 | 14−16 | 14−16 |
| Counter-Strike: Global Offensive | 55−60 | 55−60 |
| Far Cry 6 | 10−12 | 10−12 |
| Grand Theft Auto V | 9−10 | 9−10 |
| Metro Exodus | 7−8 | 7−8 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45 | 40−45 |
| Valorant | 75−80 | 75−80 |
1440p
Ultra
| Battlefield 5 | 16−18 | 16−18 |
| Cyberpunk 2077 | 6−7 | 6−7 |
| Far Cry 5 | 14−16 | 14−16 |
| Forza Horizon 4 | 18−20 | 18−20 |
| The Witcher 3: Wild Hunt | 10−11 | 10−11 |
1440p
Epic
| Fortnite | 14−16 | 14−16 |
4K
High
| Atomic Heart | 6−7 | 6−7 |
| Counter-Strike 2 | 1−2 | 1−2 |
| Far Cry 6 | 5−6 | 5−6 |
| Grand Theft Auto V | 18−20 | 18−20 |
| Metro Exodus | 3−4 | 3−4 |
| The Witcher 3: Wild Hunt | 7−8 | 7−8 |
| Valorant | 30−35 | 30−35 |
4K
Ultra
| Battlefield 5 | 8−9 | 8−9 |
| Counter-Strike 2 | 1−2 | 1−2 |
| Cyberpunk 2077 | 2−3 | 2−3 |
| Dota 2 | 27−30 | 27−30 |
| Far Cry 5 | 7−8 | 7−8 |
| Forza Horizon 4 | 12−14 | 12−14 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8 | 7−8 |
4K
Epic
| Fortnite | 7−8 | 7−8 |
This is how RTX 4000 and Radeon 660M compete in popular games:
- RTX 4000 is 335% faster in 1080p
- RTX 4000 is 362% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 35.48 | 7.47 |
| Recency | 13 November 2018 | 3 January 2023 |
| Chip lithography | 12 nm | 6 nm |
| Power consumption (TDP) | 160 Watt | 40 Watt |
RTX 4000 has a 375% higher aggregate performance score.
Radeon 660M, on the other hand, has an age advantage of 4 years, a 50% more advanced lithography process, and 75% lower power consumption.
The Quadro RTX 4000 is our recommended choice as it beats the Radeon 660M in performance tests.
Be aware that Quadro RTX 4000 is a workstation graphics card while Radeon 660M 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.
