Product Compare
NVIDIA GeForce RTX 4070 Ti SUPER vs NVIDIA CMP 170HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2024 | Sep 2021 |
| Generation | GeForce 40 | Mining GPUs |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x4 |
| Clock Speeds | ||
| Base Clock | 2340 MHz | 1140 MHz |
| Boost Clock | 2610 MHz | 1410 MHz |
| Memory Clock | 1313 MHz | 1458 MHz |
| Memory | ||
| Memory Size | 16GB | 16GB |
| Memory Type | GDDR6X | HBM2e |
| Memory Bus | 256bit | 4096bit |
| Bandwidth | 672.3GB/s | 1493GB/s |
| Render Config | ||
| SM Count | 66 | 70 |
| Shading Units | 8448 | 4480 |
| TMUs | 264 | 280 |
| ROPs | 96 | 128 |
| Tensor Cores | 264 | 280 |
| RT Cores | 66 | |
| L1 Cache | 128 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 48 MB | 8 MB |
| Theoretical Performance | ||
| Pixel Rate | 250.6 GPixel/s | 180.5 GPixel/s |
| Texture Rate | 689.0 GTexel/s | 394.8 GTexel/s |
| FP16 (half) | 44.10 TFLOPS | 50.53 TFLOPS |
| FP32 (float) | 44.10 TFLOPS | 12.63 TFLOPS |
| FP64 (double) | 689.0 GFLOPS | 6.317 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD103 | GA100 |
| GPU Variant | AD103-275-A1 | GA100-105F-A1 |
| Architecture | Ada Lovelace | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 7 nm |
| Transistors | 45.9 billion | 54.2 billion |
| Die Size | 379 mm² | 826 mm² |
| Board Design | ||
| TDP | 285W | 250W |
| Suggested PSU | 600 W | 600 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.9 | 8.0 |
| Shader Model | 6.7 | N/A |