AMD Radeon RX 7900 XT vs NVIDIA GeForce RTX 4080

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

Only show differences

Better figure, where one is clearly better

Share comparison

Radeon RX 7900 XT compared with GeForce RTX 4080

	AMDRadeon RX 7900 XT	NVIDIAGeForce RTX 4080
Overview
Released
Released	December 2022	November 2022
Performance
Chip maker
Chip maker	AMD	NVIDIA
Architecture
Architecture	RDNA 3	Ada Lovelace
Shader cores
Shader cores	5,376	9,728
Boost clock
Boost clock	2,400 MHz	2,510 MHz (better)
Architecture
Architecture	84 compute units, 192 ROPs; game clock 2000 MHz; 58 billion transistors	AD103; 76 Streaming Multiprocessors. Specifications describe NVIDIA's reference card; the photo shows PNY's original RTX 4080 VERTO Triple Fan, whose cooler and dimensions differ.
Manufacturing process
Manufacturing process	Chiplet design; 5nm Graphics Compute Die with 6nm Memory Cache Dies	TSMC 4N; 45.9 billion transistors; 378.6 mm² die
Ray tracing
Ray tracing	84 second-generation Ray Accelerators	76 third-generation RT Cores; 113 RT TFLOPS
AI cores
AI cores	168 AI Accelerators; 103 TOPS INT8	304 fourth-generation Tensor Cores; 780 AI TOPS
Upscaling and frame generation
Upscaling and frame generation	AMD FSR, Radeon Super Resolution	DLSS 3.5 with Super Resolution, DLAA, Ray Reconstruction and Frame Generation
Base clock
Base clock	–	2.21 GHz on the current NVIDIA specification page; PNY's stock-clock VERTO lists 2,205 MHz base, while NVIDIA's Ada architecture whitepaper gives 2,505 MHz boost (current page rounds boost to 2.51 GHz)
Cache
Cache	80 MB AMD Infinity Cache (second generation)	65,536 KB L2
Memory
Video memory
Video memory	20 GB GDDR6 (better)	16 GB GDDR6X
Memory bus
Memory bus	320-bit (better)	256-bit
Memory bandwidth
Memory bandwidth	800 GB/s (better)	716.8 GB/s
Memory detail
Memory detail	GDDR6 at up to 20 Gbps; AMD quotes up to 2900 GB/s effective bandwidth with Infinity Cache	22.4 Gbps GDDR6X
Connections and power
Board power
Board power	315 W (better)	320 W
Interface
Interface	–	PCIe 4.0
Display outputs
Display outputs	DisplayPort 2.1 (UHBR 13.5), HDMI 2.1a, USB Type-C	3 × DisplayPort 1.4a, 1 × HDMI 2.1a; up to 4 displays; HDCP 2.3
Maximum resolution
Maximum resolution	Up to 4K 480 Hz or 8K 165 Hz over DisplayPort 2.1	4K at 240 Hz or 8K at 60 Hz with DSC and HDR
Power connector
Power connector	2 × 8-pin	3 × PCIe 8-pin cables through the included adapter, or 1 × 450 W or greater PCIe Gen 5 cable (Founders Edition)
Recommended power supply
Recommended power supply	750 W	750 W; NVIDIA recommends another 36 mm of clearance for the power cable
Slot width
Slot width	2.5-slot (reference card)	3-slot (Founders Edition)
Size (reference card)
Size (reference card)	276 mm long, 2.5-slot (reference card)	304 × 137 mm, 3-slot; NVIDIA's system-clearance guide specifies 61 mm thickness (Founders Edition)
Video encode and decode
Video encode and decode	H.264, HEVC and AV1 encode and decode	2 × eighth-generation NVENC, fifth-generation NVDEC; AV1 encode and decode