NVIDIA GeForce GTX 1070 vs NVIDIA GeForce RTX 5070 Ti

Every spec side by side, from each maker's published figures.

Better figure, where one is clearly better

GeForce GTX 1070 compared with GeForce RTX 5070 Ti
NVIDIAGeForce GTX 1070NVIDIAGeForce RTX 5070 Ti
Overview
ReleasedJune 2016February 2025
Performance
Chip makerNVIDIANVIDIA
ArchitecturePascalBlackwell
Shader cores1,9208,960
Boost clock1,683 MHz2,452 MHz (better)
ArchitectureMain figures and photo describe the Founders Edition, verified in MSI's retained datasheet. Partner boards can use different clocks, coolers and connectors.GB203 GPU; 70 SMs
Manufacturing process–TSMC 4nm (4N NVIDIA custom process); 45.6 billion transistors; 378 mm² die
Ray tracingNo dedicated RT Cores70 fourth-generation RT Cores; 133 RT TFLOPS
AI coresNo Tensor Cores280 fifth-generation Tensor Cores; 1406 AI TOPS
Upscaling and frame generationNo NVIDIA DLSSDLSS 4.5 with Super Resolution, DLAA, Ray Reconstruction, Frame Generation, Multi Frame Generation and Dynamic Multi Frame Generation
Base clock1506 MHz2.30 GHz
Cache–48 MB L2
Memory
Video memory8 GB GDDR516 GB GDDR7 (better)
Memory bus256-bit256-bit
Memory bandwidth–896 GB/s
Memory detail8008 MHz effective memory speed (MSI Founders Edition); numerical bandwidth omitted because the maker source used does not publish it.GDDR7 at 28 Gbps
Connections and power
Board power150 W (better)300 W
InterfacePCIe 3.0PCIe 5.0
Display outputs3 × DisplayPort 1.4, 1 × HDMI 2.0b and 1 × dual-link DVI-D; up to 4 displays; HDCP 2.23 × DisplayPort 2.1b (UHBR20), 1 × HDMI 2.1b; up to 4 displays; HDCP 2.3
Maximum resolution7680 × 43204K at 480 Hz or 8K at 165 Hz with DSC
Power connector1 × 8-pin1 × 300 W or greater PCIe Gen 5 cable, or 2 × PCIe 8-pin cables with the adapter in the box
Recommended power supply500 W750 W
Video encode and decode–2 × ninth-generation NVENC, 1 × sixth-generation NVDEC; AV1 encode and decode
Size (reference card)268 × 111 × 38 mm and 1096 g (MSI Founders Edition)–

More comparisons