Product Compare
NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB vs AMD Radeon 680M
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jul 2022 | Jan 2022 |
| Generation | GeForce 30 Mobile | Navi II IGP |
| Type | Mobile | Integrated |
| Bus Interface | PCIe 4.0 x8 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Base Clock | 757 MHz | 2000 MHz |
| Boost Clock | 1125 MHz | 2200 MHz |
| Memory Clock | 1375 MHz | System Shared |
| Memory | ||
| Memory Size | 4GB | System Shared |
| Memory Type | GDDR6 | System Shared |
| Memory Bus | 128bit | System Shared |
| Bandwidth | 176.0GB/s | System Dependent |
| Render Config | ||
| SM Count | 16 | |
| Shading Units | 2048 | 768 |
| TMUs | 64 | 48 |
| ROPs | 32 | 32 |
| Tensor Cores | 64 | |
| RT Cores | 16 | 12 |
| L1 Cache | 128 KB (per SM) | 128 KB per Array |
| L2 Cache | 2 MB | 2 MB |
| Compute Units | 12 | |
| Theoretical Performance | ||
| Pixel Rate | 36.00 GPixel/s | 70.40 GPixel/s |
| Texture Rate | 72.00 GTexel/s | 105.6 GTexel/s |
| FP16 (half) | 4.608 TFLOPS | 6.758 TFLOPS |
| FP32 (float) | 4.608 TFLOPS | 3.379 TFLOPS |
| FP64 (double) | 72.00 GFLOPS | 211.2 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA107 | Rembrandt |
| Architecture | Ampere | RDNA 2.0 |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 6 nm |
| Transistors | 8.7 billion | 13.1 billion |
| Die Size | 200 mm² | 208 mm² |
| Board Design | ||
| TDP | 35W | 50W |
| Outputs | Portable Device Dependent | Portable Device Dependent |
| Power Connectors | None | None |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.6 | |
| Shader Model | 6.7 | 6.7 |