AMD Radeon RX 9070 XT vs NVIDIA GeForce RTX 5070 Ti

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

Better figure, where one is clearly better

Radeon RX 9070 XT compared with GeForce RTX 5070 Ti
AMDRadeon RX 9070 XTNVIDIAGeForce RTX 5070 Ti
Overview
ReleasedMarch 2025February 2025
Performance
Chip makerAMDNVIDIA
ArchitectureRDNA 4Blackwell
Shader cores4,0968,960
Boost clock2,970 MHz (better)2,452 MHz
Architecture64 compute units, 128 ROPs; game clock 2400 MHz; 53.9 billion transistorsGB203 GPU; 70 SMs
Manufacturing process–TSMC 4nm (4N NVIDIA custom process); 45.6 billion transistors; 378 mm² die
Ray tracing64 third-generation Ray Accelerators70 fourth-generation RT Cores; 133 RT TFLOPS
AI cores128 AI Accelerators; up to 779 TOPS INT8 or 1557 TOPS INT4 with structured sparsity280 fifth-generation Tensor Cores; 1406 AI TOPS
Upscaling and frame generationAMD FSR "Redstone" (including FSR 4 upscaling), AMD Fluid Motion Frames, Radeon Super ResolutionDLSS 4.5 with Super Resolution, DLAA, Ray Reconstruction, Frame Generation, Multi Frame Generation and Dynamic Multi Frame Generation
Base clock–2.30 GHz
Cache64 MB AMD Infinity Cache48 MB L2
Memory
Video memory16 GB GDDR616 GB GDDR7
Memory bus256-bit256-bit
Memory bandwidth640 GB/s896 GB/s (better)
Memory detailGDDR6 at up to 20 GbpsGDDR7 at 28 Gbps
Connections and power
Board power304 W300 W (better)
InterfacePCIe 5.0 x16PCIe 5.0
Display outputsDisplayPort 2.1a, HDMI 2.1b (number of ports depends on the card)3 × DisplayPort 2.1b (UHBR20), 1 × HDMI 2.1b; up to 4 displays; HDCP 2.3
Maximum resolution–4K at 480 Hz or 8K at 165 Hz with DSC
Power connector2 × 8-pin1 × 300 W or greater PCIe Gen 5 cable, or 2 × PCIe 8-pin cables with the adapter in the box
Recommended power supply750 W750 W
Video encode and decodeH.264, HEVC and AV1 encode and decode2 × ninth-generation NVENC, 1 × sixth-generation NVDEC; AV1 encode and decode

More comparisons