NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 4080 SUPER
Better figure, where one is clearly better
| NVIDIAGeForce RTX 3070 | NVIDIAGeForce RTX 4080 SUPER | |
|---|---|---|
| Overview | ||
| Released | October 2020 | January 2024 |
| Performance | ||
| Chip maker | NVIDIA | NVIDIA |
| Architecture | Ampere | Ada Lovelace |
| Shader cores | 5,888 | 10,240 |
| Boost clock | 1,730 MHz | 2,550 MHz (better) |
| Architecture | GA104; 46 Streaming Multiprocessors. NVIDIA reference specifications; photo shows PNY's stock-clock UPRISING Dual Fan LHR revision, whose cooler and dimensions differ from the Founders Edition. | – |
| Manufacturing process | Samsung 8 nm 8N NVIDIA custom process; 17.4 billion transistors; 392.5 mm² die | – |
| Ray tracing | 46 second-generation RT Cores | Third-generation RT Cores; 121 RT TFLOPS |
| AI cores | 184 third-generation Tensor Cores | Fourth-generation Tensor Cores; 836 AI TOPS |
| Upscaling and frame generation | NVIDIA DLSS upscaling; no DLSS Frame Generation | DLSS 3.5 with Super Resolution, DLAA, Ray Reconstruction and Frame Generation |
| Base clock | 1.50 GHz; the NVIDIA architecture whitepaper specifies 1,725 MHz boost, rounded to 1.73 GHz on the current specification page | 2.29 GHz |
| Cache | 4,096 KB L2 | 64 MB L2 |
| Memory | ||
| Video memory | 8 GB GDDR6 | 16 GB GDDR6X (better) |
| Memory bus | 256-bit | 256-bit |
| Memory bandwidth | 448 GB/s | 736 GB/s (better) |
| Memory detail | 14 Gbps GDDR6 | GDDR6X at 23 Gbps |
| Connections and power | ||
| Board power | 220 W (better) | 320 W |
| Interface | PCIe 4.0 | PCIe 4.0 |
| Display outputs | 3 × DisplayPort 1.4a, 1 × HDMI 2.1; up to 4 displays; HDCP 2.3 | 3 × DisplayPort 1.4a, 1 × HDMI 2.1a; up to 4 displays; HDCP 2.3 |
| Maximum resolution | 7680 × 4320; HDMI supports 4K 120 Hz HDR or 8K 60 Hz HDR | 4K at 240 Hz or 8K at 60 Hz with DSC, HDR |
| Power connector | 1 × PCIe 8-pin cable through the included adapter to 1 × 12-pin (Founders Edition) | 1 × 450 W or greater PCIe Gen 5 cable, or 3 × PCIe 8-pin cables with the adapter in the box |
| Recommended power supply | 650 W, based on NVIDIA's Intel Core i9-10900K test system | 750 W |
| Slot width | 2-slot (Founders Edition) | 3-slot (Founders Edition) |
| Size (reference card) | 242 × 112 mm, 2-slot (Founders Edition) | 304 × 137 mm, 3-slot (Founders Edition) |
| Video encode and decode | Seventh-generation NVENC, fifth-generation NVDEC; hardware AV1 decode, no AV1 encode | 2 × eighth-generation NVENC, 1 × fifth-generation NVDEC; AV1 encode and decode |
More comparisons
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5050
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5050
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5060
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5060
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5060 Ti
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5060 Ti
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5090
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 5090
- NVIDIA GeForce RTX 4080 vs NVIDIA GeForce RTX 4080 SUPER
- NVIDIA GeForce RTX 3080 Ti vs NVIDIA GeForce RTX 4080 SUPER

