NVIDIA GeForce RTX 2060 vs NVIDIA GeForce RTX 3060

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

Only show differences

Better figure, where one is clearly better

Share comparison

GeForce RTX 2060 compared with GeForce RTX 3060

	NVIDIAGeForce RTX 2060	NVIDIAGeForce RTX 3060
Overview
Released
Released	January 2019	February 2021
Performance
Chip maker
Chip maker	NVIDIA	NVIDIA
Architecture
Architecture	Turing	Ampere
Shader cores
Shader cores	1,920 or 2,176	3,584
Boost clock
Boost clock	1,680 MHz or 1,650 MHz	1,780 MHz
Architecture
Architecture	NVIDIA reference GPU specifications; photo shows PNY's stock-clock 6 GB Blower partner card, whose cooler, dimensions and display connectors differ from the Founders Edition. The later 12 GB card has 2,176 CUDA cores rather than 1,920.	NVIDIA reference GPU specifications; photo shows Gainward's stock-clock 12 GB Ghost partner card. NVIDIA announced worldwide partner availability of the 8 GB revision from November 2022.
Manufacturing process
Manufacturing process	–	8 nm (Gainward Ghost datasheet)
Ray tracing
Ray tracing	First-generation RT Cores; NVIDIA's original launch specification lists 30 RT Cores and 5 Giga Rays/s for 6 GB	Second-generation RT Cores
AI cores
AI cores	Second-generation Tensor Cores; 240 on the original 6 GB model according to NVIDIA's launch specification	Third-generation Tensor Cores
Upscaling and frame generation
Upscaling and frame generation	NVIDIA DLSS 2.0 upscaling; no DLSS Frame Generation	NVIDIA DLSS upscaling; no DLSS Frame Generation
Base clock
Base clock	1,365 MHz base and 1,680 MHz boost (6 GB); 1,470 MHz base and 1,650 MHz boost (12 GB)	1.32 GHz; NVIDIA rounds boost to 1.78 GHz, while Gainward's stock-clock 12 GB Ghost and 8 GB Pegasus both specify 1,777 MHz
Memory
Video memory
Video memory	6 GB GDDR6 or 12 GB GDDR6	12 GB GDDR6 or 8 GB GDDR6
Memory bus
Memory bus	192-bit	192-bit or 128-bit
Memory bandwidth
Memory bandwidth	336 GB/s	360 GB/s or 240 GB/s
Memory detail
Memory detail	14 Gbps GDDR6 on a 192-bit bus with 336 GB/s bandwidth on both revisions	15 Gbps GDDR6. Original 12 GB is 192-bit with 360 GB/s bandwidth (Gainward Ghost); later 8 GB is 128-bit with 240 GB/s (Gainward Pegasus).
Connections and power
Board power
Board power	160 W or 185 W	170 W
Interface
Interface	PCIe 3.0	PCIe 4.0
Display outputs
Display outputs	Original 6 GB NVIDIA page lists DisplayPort 1.4a, HDMI 2.0b, USB-C/VirtualLink and DVI-DL. The 12 GB regional table lists DisplayPort, HDMI and DVI-DL without USB-C; the current combined comparison table also omits USB-C. Up to 4 displays; HDCP 2.2. Partner connectors vary.	3 × DisplayPort 1.4a, 1 × HDMI 2.1; up to 4 displays; HDCP 2.3; check the chosen partner card
Maximum resolution
Maximum resolution	7680 × 4320; original specification states 4K 144 Hz or 8K 60 Hz over DisplayPort with DSC	7680 × 4320; HDMI supports 4K 120 Hz HDR or 8K 60 Hz HDR
Power connector
Power connector	1 × PCIe 8-pin for both reference specifications	Varies by partner card; Gainward's 12 GB Ghost and 8 GB Pegasus each specify 1 × PCIe 8-pin
Recommended power supply
Recommended power supply	500 W (6 GB); 550 W (12 GB); NVIDIA reference power specifications	550 W on NVIDIA's reference specification, based on an Intel Core i9-10900K system
Slot width
Slot width	2-slot (original 6 GB Founders Edition); 12 GB partner cards vary	Varies by partner card; no Founders Edition model
Size (reference card)
Size (reference card)	228.60 × 112.6 mm, 2-slot (original 6 GB Founders Edition). NVIDIA's regional table repeats these dimensions for 12 GB, but no separate 12 GB Founders Edition design was verified.	–
Video encode and decode
Video encode and decode	Seventh-generation NVENC, fourth-generation NVDEC (NVIDIA comparison table); no hardware AV1 encode	Seventh-generation NVENC, fifth-generation NVDEC; hardware AV1 decode, no AV1 encode