GeForce GTX 660 OEM vs RTX PRO 2000 Blackwell
Aggregate performance score
We've compared RTX PRO 2000 Blackwell with GeForce GTX 660 OEM, including specs and performance data.
RTX PRO 2000 Blackwell outperforms 660 OEM by a whopping 1009% 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 | 166 | 794 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 37.43 | 1.82 |
| Architecture | Blackwell 2.0 (2025−2026) | Kepler (2012−2018) |
| GPU code name | GB206 | GK104 |
| Market segment | Workstation | Desktop |
| Release date | 11 August 2025 (less than a year ago) | 22 August 2012 (13 years ago) |
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 | 4352 | 1152 |
| Core clock speed | 790 MHz | 823 MHz |
| Boost clock speed | 1950 MHz | 888 MHz |
| Number of transistors | 21,900 million | 3,540 million |
| Manufacturing process technology | 5 nm | 28 nm |
| Power consumption (TDP) | 70 Watt | 130 Watt |
| Texture fill rate | 265.2 | 85.25 |
| Floating-point processing power | 16.97 TFLOPS | 2.046 TFLOPS |
| ROPs | 64 | 32 |
| TMUs | 136 | 96 |
| Tensor Cores | 136 | no data |
| Ray Tracing Cores | 34 | no data |
| L1 Cache | 4.3 MB | 96 KB |
| L2 Cache | 32 MB | 512 KB |
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 5.0 x8 | PCIe 3.0 x16 |
| Length | 167 mm | 241 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | None | 1x 6-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 | GDDR7 | GDDR5 |
| Maximum RAM amount | 16 GB | 2 GB |
| Memory bus width | 128 Bit | 256 Bit |
| Memory clock speed | 1125 MHz | 1400 MHz |
| Memory bandwidth | 288.0 GB/s | 179.2 GB/s |
| Resizable BAR | + | - |
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 | 4x mini-DisplayPort 2.1b | 2x DVI, 1x HDMI, 1x DisplayPort |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 (11_0) |
| Shader Model | 6.8 | 5.1 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.2 |
| Vulkan | 1.4 | 1.1.126 |
| CUDA | 12.0 | 3.0 |
| DLSS | + | - |
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Pros & cons summary
| Performance score | 32.49 | 2.93 |
| Recency | 11 August 2025 | 22 August 2012 |
| Maximum RAM amount | 16 GB | 2 GB |
| Chip lithography | 5 nm | 28 nm |
| Power consumption (TDP) | 70 Watt | 130 Watt |
RTX PRO 2000 Blackwell has a 1008.9% higher aggregate performance score, an age advantage of 12 years, a 700% higher maximum VRAM amount, a 460% more advanced lithography process, and 85.7% lower power consumption.
The RTX PRO 2000 Blackwell is our recommended choice as it beats the GeForce GTX 660 OEM in performance tests.
Be aware that RTX PRO 2000 Blackwell is a workstation graphics card while GeForce GTX 660 OEM 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.
