NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5080
Better figure, where one is clearly better
| NVIDIAGeForce RTX 4070 Ti | NVIDIAGeForce RTX 5080 | |
|---|---|---|
| Overview | ||
| Released | January 2023 | January 2025 |
| Performance | ||
| Chip maker | NVIDIA | NVIDIA |
| Architecture | Ada Lovelace | Blackwell |
| Shader cores | 7,680 | 10,752 |
| Boost clock | 2,610 MHz | 2,617 MHz (better) |
| Architecture | NVIDIA reference GPU specifications; partner cards have different coolers and may use factory overclocks. Photo shows PNY's stock-clock RTX 4070 Ti VERTO Triple Fan, not the later RTX 4070 Ti SUPER. | GB203 GPU; 84 SMs |
| Manufacturing process | – | TSMC 4nm (4N NVIDIA custom process); 45.6 billion transistors; 378 mm² die |
| Ray tracing | Third-generation RT Cores; 93 RT TFLOPS | 84 fourth-generation RT Cores; 171 RT TFLOPS |
| AI cores | Fourth-generation Tensor Cores; 641 AI TOPS | 336 fifth-generation Tensor Cores; 1801 AI TOPS |
| Upscaling and frame generation | DLSS 3.5 with Super Resolution, DLAA, Ray Reconstruction and Frame Generation | DLSS 4.5 with Super Resolution, DLAA, Ray Reconstruction, Frame Generation, Multi Frame Generation and Dynamic Multi Frame Generation |
| Base clock | 2.31 GHz | 2.30 GHz |
| Cache | – | 64 MB L2 |
| Memory | ||
| Video memory | 12 GB GDDR6X | 16 GB GDDR7 (better) |
| Memory bus | 192-bit | 256-bit (better) |
| Memory bandwidth | 504 GB/s | 960 GB/s (better) |
| Memory detail | 21 Gbps GDDR6X (PNY stock-clock VERTO specification) | GDDR7 at 30 Gbps |
| Connections and power | ||
| Board power | 285 W (better) | 360 W |
| Interface | PCIe 4.0 | PCIe 5.0 |
| Display outputs | 3 × DisplayPort 1.4a, 1 × HDMI 2.1a; up to 4 displays; HDCP 2.3 | 3 × DisplayPort 2.1b (UHBR20), 1 × HDMI 2.1b; up to 4 displays; HDCP 2.3 |
| Maximum resolution | 4K at 240 Hz or 8K at 60 Hz with DSC and HDR | 4K at 480 Hz or 8K at 165 Hz with DSC |
| Power connector | 2 × PCIe 8-pin cables through an adapter, or 1 × 300 W or greater PCIe Gen 5 cable; check the chosen partner card | 1 × 450 W or greater PCIe Gen 5 cable, or 3 × PCIe 8-pin cables with the adapter in the box |
| Recommended power supply | 700 W | 850 W |
| Slot width | Varies by manufacturer; NVIDIA publishes no Founders Edition dimensions | 2-slot (Founders Edition) |
| Size (reference card) | – | 304 × 137 mm, 2-slot (Founders Edition) |
| Video encode and decode | 2 × eighth-generation NVENC, fifth-generation NVDEC; AV1 encode and decode | 2 × ninth-generation NVENC, 2 × sixth-generation NVDEC; AV1 encode and decode |
More comparisons
- NVIDIA GeForce RTX 5050 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5050
- NVIDIA GeForce RTX 5060 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5060
- NVIDIA GeForce RTX 5060 Ti vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5060 Ti
- NVIDIA GeForce RTX 5070 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 4070 Ti vs NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 5070 Ti vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 3080 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4080 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti SUPER vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 5080 vs NVIDIA GeForce RTX 5090
- NVIDIA GeForce RTX 4070 SUPER vs NVIDIA GeForce RTX 5080

