NVIDIA GeForce 825M vs NVIDIA GeForce GTX 660M
What is the difference between NVIDIA GeForce 825M and NVIDIA GeForce GTX 660M. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GK208 | GPU Name | GK107 |
| Kepler 2.0 | Architecture | Kepler |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 28 nm |
| 1,020 million | Transistors | 1,270 million |
| 87 mm² | Die Size | 118 mm² |
Graphics Card
| Jan 27th, 2014 | Release Date | Mar 22nd, 2012 |
| GeForce 800M | Family | GeForce 600M |
| End-of-life | Production | End-of-life |
| GeForce 700M | Predecessor | GeForce 500M |
| PCIe 3.0 x8 | Bus Interface | MXM-B (3.0) |
Memory
| 1024 MB | Memory Size | 1024 MB |
| DDR3 | Memory Type | GDDR5 |
| 64 bit | Memory Bus | 128 bit |
| 14.40 GB/s | Bandwidth | 64.00 GB/s |
Performance
| 7.528 GPixel/s | Pixel fillrate | 7.600 GPixel/s |
| 30.11 GTexel/s | Texture fillrate | 30.40 GTexel/s |
| 722.7 GFLOPS | FP32 (float) performance | 729.6 GFLOPS |
| 30.11 GFLOPS (1:24) | FP64 (double) performance | 30.40 GFLOPS (1:24) |
Clock Speeds
| 850 MHz | Base Clock | 835 MHz |
| 941 MHz | Boost Clock | 950 MHz |
| 900 MHz 1800 Mbps effective | Memory Clock | 1000 MHz 4 Gbps effective |
Render Config
| 384 | Shading Units | 384 |
| 32 | TMUs | 32 |
| 8 | ROPs | 16 |
| 16 KB (per SMX) | L1 Cache | 16 KB (per SMX) |
| 512 KB | L2 Cache | 256 KB |
Board Design
| IGP | Slot Width | MXM Module |
| 33 W | Thermal design power (TDP) | 50 W |
| No outputs | Display Connectors | No outputs |
API support
| 12 (11_0) | DirectX | 12 (11_0) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 3.0 |
| 1.1 | Vulkan | 1.1 |
| 5.1 | Shader Model | 5.1 |
| 3.5 | CUDA | 3.0 |