Product Compare
NVIDIA GB10 vs NVIDIA GeForce RTX 4060 Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2025 | Jan 2023 |
| Generation | Server Blackwell | GeForce 40 Mobile |
| Type | Desktop | Mobile |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Base Clock | 1665 MHz | 1140 MHz |
| Boost Clock | 2418 MHz | 1470 MHz |
| Memory Clock | 1067 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 128GB | 8GB |
| Memory Type | LPDDR5X | GDDR6 |
| Memory Bus | 256bit | 128bit |
| Bandwidth | 273.2GB/s | 256.0GB/s |
| Render Config | ||
| SM Count | 48 | 24 |
| Shading Units | 6144 | 3072 |
| TMUs | 384 | 96 |
| ROPs | 48 | 48 |
| Tensor Cores | 384 | 96 |
| RT Cores | 48 | 24 |
| L1 Cache | 256 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 50 MB | 32 MB |
| Theoretical Performance | ||
| Pixel Rate | 116.1 GPixel/s | 70.56 GPixel/s |
| Texture Rate | 928.5 GTexel/s | 141.1 GTexel/s |
| FP16 (half) | 29.71 TFLOPS | 9.032 TFLOPS |
| FP32 (float) | 29.71 TFLOPS | 9.032 TFLOPS |
| FP64 (double) | 464.3 GFLOPS | 141.1 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB20B | AD107 |
| Architecture | Blackwell 2.0 | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 3 nm | 5 nm |
| Transistors | Unknown | 18.9 billion |
| Die Size | Unknown | 159 mm² |
| GPU Variant | GN21-X4 | |
| Board Design | ||
| TDP | 140W | 35W |
| Suggested PSU | 300 W | |
| Outputs | 1x HDMI | Portable Device Dependent |
| Power Connectors | None | None |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 12.1 | 8.9 |
| Shader Model | N/A | 6.8 |