AMD Radeon RX 6700 XT vs NVIDIA GeForce RTX 2070 SUPER

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 6700 XT compared with GeForce RTX 2070 SUPER

	AMDRadeon RX 6700 XT	NVIDIAGeForce RTX 2070 SUPER
Overview
Released
Released	March 2021	July 2019
Performance
Chip maker
Chip maker	AMD	NVIDIA
Architecture
Architecture	RDNA 2	Turing
Shader cores
Shader cores	2,560	2,560
Boost clock
Boost clock	2,581 MHz (better)	1,770 MHz
Architecture
Architecture	AMD reference specification; 40 compute units and 17.2 billion transistors. AMD's current product table labels 1 March 2021 as the launch date, but its announcement specifies 18 March as the first on-sale date used here.	NVIDIA reference/Founders Edition GPU figures; photo shows PNY's stock-clock Dual Fan partner card
Manufacturing process
Manufacturing process	7 nm	–
Ray tracing
Ray tracing	40 Ray Accelerators; DirectX Raytracing support	First-generation RT Cores
AI cores
AI cores	–	Second-generation Tensor Cores
Upscaling and frame generation
Upscaling and frame generation	AMD FidelityFX Super Resolution (FSR); AMD Radeon Super Resolution	NVIDIA DLSS super resolution; no DLSS frame generation
Base clock
Base clock	2321 MHz base, 2424 MHz game frequency and up to 2581 MHz boost; AMD defines boost for bursty workloads rather than sustained gaming	NVIDIA's current comparison rounds the base clock to 1.61 GHz; PNY publishes 1,605 MHz
Cache
Cache	96 MB AMD Infinity Cache	–
Memory
Video memory
Video memory	12 GB GDDR6 (better)	8 GB GDDR6
Memory bus
Memory bus	192-bit	256-bit (better)
Memory bandwidth
Memory bandwidth	384 GB/s	448 GB/s (better)
Memory detail
Memory detail	Up to 16 Gbps GDDR6; 384 GB/s physical memory bandwidth. AMD separately claims up to 1278 GB/s effective bandwidth including Infinity Cache; this is not used as the physical bandwidth figure.	PNY publishes 14 Gbps GDDR6 and 448 GB/sec bandwidth
Connections and power
Board power
Board power	230 W	215 W (better)
Interface
Interface	PCIe 4.0	PCIe 3.0
Display outputs
Display outputs	DisplayPort 1.4a and HDMI 2.1 supporting 4K 120 Hz or 8K 60 Hz with VRR	Pictured PNY Dual Fan has 3 × DisplayPort 1.4 and 1 × HDMI 2.0b. PCWorld's Founders Edition review also documents USB-C; NVIDIA's current comparison table lists only DisplayPort and HDMI for this model.
Maximum resolution
Maximum resolution	–	7680 × 4320; NVIDIA specifies support for four displays
Power connector
Power connector	1 × PCIe 8-pin and 1 × PCIe 6-pin	1 × 6-pin and 1 × 8-pin
Recommended power supply
Recommended power supply	650 W	NVIDIA specifies 650 W; requirements depend on the system
Slot width
Slot width	2-slot (AMD reference)	Two slots for the Founders Edition and pictured PNY Dual Fan
Size (reference card)
Size (reference card)	267 mm long (AMD reference); no reference width or height verified	NVIDIA reference/Founders Edition is 266.74 × 115.7 mm; pictured PNY Dual Fan is 1.57 × 9.25 × 4.41 inches
Video encode and decode
Video encode and decode	Hardware AV1 decoding; H.264 and H.265/HEVC encode and decode	Seventh-generation NVIDIA Encoder and fourth-generation Decoder; PNY specifies PCIe 3.0 x16. NVIDIA specifies NVLink support.