AMD Radeon RX 6700 XT vs NVIDIA GeForce RTX 3060 Ti

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 3060 Ti

	AMDRadeon RX 6700 XT	NVIDIAGeForce RTX 3060 Ti
Overview
Released
Released	March 2021	December 2020
Performance
Chip maker
Chip maker	AMD	NVIDIA
Architecture
Architecture	RDNA 2	Ampere
Shader cores
Shader cores	2,560	4,864
Boost clock
Boost clock	2,581 MHz (better)	1,670 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 specifications; photo shows Gainward's original GDDR6 Ghost partner card, whose cooler and dimensions differ from the Founders Edition. NVIDIA announced worldwide partner availability of the GDDR6X revision from November 2022.
Manufacturing process
Manufacturing process	7 nm	–
Ray tracing
Ray tracing	40 Ray Accelerators; DirectX Raytracing support	Second-generation RT Cores
AI cores
AI cores	–	Third-generation Tensor Cores
Upscaling and frame generation
Upscaling and frame generation	AMD FidelityFX Super Resolution (FSR); AMD Radeon Super Resolution	NVIDIA DLSS upscaling; 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	1.41 GHz; NVIDIA rounds boost to 1.67 GHz. Gainward's original Ghost and PNY's GDDR6X VERTO both specify 1,665 MHz boost.
Cache
Cache	96 MB AMD Infinity Cache	–
Memory
Video memory
Video memory	12 GB GDDR6 (better)	8 GB GDDR6 or 8 GB GDDR6X
Memory bus
Memory bus	192-bit	256-bit (better)
Memory bandwidth
Memory bandwidth	384 GB/s	448 GB/s or 608 GB/s
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.	Original GDDR6 is 14 Gbps and 448 GB/s (Gainward Ghost); later GDDR6X is 19 Gbps and 608 GB/s (PNY stock-clock VERTO). Both have 8 GB on a 256-bit bus.
Connections and power
Board power
Board power	230 W	200 W or –
Interface
Interface	PCIe 4.0	PCIe 4.0
Display outputs
Display outputs	DisplayPort 1.4a and HDMI 2.1 supporting 4K 120 Hz or 8K 60 Hz with VRR	3 × DisplayPort 1.4a, 1 × HDMI 2.1; up to 4 displays; HDCP 2.3
Maximum resolution
Maximum resolution	–	7680 × 4320; HDMI supports 4K 120 Hz HDR or 8K 60 Hz HDR
Power connector
Power connector	1 × PCIe 8-pin and 1 × PCIe 6-pin	1 × PCIe 8-pin cable through the included adapter to 1 × 12-pin (original GDDR6 Founders Edition); check the maker for GDDR6X partner cards
Recommended power supply
Recommended power supply	650 W	600 W for the original Founders Edition. NVIDIA's current table lists 200 W card power without separating memory revisions; PNY publishes 225 W and a 650 W system recommendation for its GDDR6X VERTO. Its board power is not treated as a verified universal GDDR6X reference figure.
Slot width
Slot width	2-slot (AMD reference)	2-slot (original GDDR6 Founders Edition); GDDR6X partner cards vary
Size (reference card)
Size (reference card)	267 mm long (AMD reference); no reference width or height verified	242 × 112 mm, 2-slot (original GDDR6 Founders Edition); no separate GDDR6X reference geometry verified
Video encode and decode
Video encode and decode	Hardware AV1 decoding; H.264 and H.265/HEVC encode and decode	Seventh-generation NVENC, fifth-generation NVDEC; hardware AV1 decode, no AV1 encode