NVIDIA GeForce RTX 2060 vs NVIDIA GeForce RTX 5090

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 5090

	NVIDIAGeForce RTX 2060	NVIDIAGeForce RTX 5090
Overview
Released
Released	January 2019	January 2025
Performance
Chip maker
Chip maker	NVIDIA	NVIDIA
Architecture
Architecture	Turing	Blackwell
Shader cores
Shader cores	1,920 or 2,176	21,760
Boost clock
Boost clock	1,680 MHz or 1,650 MHz	2,407 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.	GB202 GPU; 170 SMs, 680 texture units, 176 ROPs
Manufacturing process
Manufacturing process	–	TSMC 4nm (4N NVIDIA custom process); 92.2 billion transistors; 750 mm² die
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	170 fourth-generation RT Cores; 318 RT TFLOPS
AI cores
AI cores	Second-generation Tensor Cores; 240 on the original 6 GB model according to NVIDIA's launch specification	680 fifth-generation Tensor Cores; 3352 AI TOPS
Upscaling and frame generation
Upscaling and frame generation	NVIDIA DLSS 2.0 upscaling; no DLSS Frame Generation	DLSS 4.5 with Super Resolution, DLAA, Ray Reconstruction, Frame Generation, Multi Frame Generation and Dynamic Multi 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)	2.01 GHz
Cache
Cache	–	96 MB L2
Memory
Video memory
Video memory	6 GB GDDR6 or 12 GB GDDR6	32 GB GDDR7
Memory bus
Memory bus	192-bit	512-bit (better)
Memory bandwidth
Memory bandwidth	336 GB/s	1,792 GB/s (better)
Memory detail
Memory detail	14 Gbps GDDR6 on a 192-bit bus with 336 GB/s bandwidth on both revisions	GDDR7 at 28 Gbps
Connections and power
Board power
Board power	160 W or 185 W	575 W
Interface
Interface	PCIe 3.0	PCIe 5.0
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 2.1b (UHBR20), 1 × HDMI 2.1b; up to 4 displays; HDCP 2.3
Maximum resolution
Maximum resolution	7680 × 4320; original specification states 4K 144 Hz or 8K 60 Hz over DisplayPort with DSC	4K at 480 Hz or 8K at 165 Hz with DSC
Power connector
Power connector	1 × PCIe 8-pin for both reference specifications	1 × 600 W PCIe Gen 5 cable, or 4 × PCIe 8-pin cables with the adapter in the box
Recommended power supply
Recommended power supply	500 W (6 GB); 550 W (12 GB); NVIDIA reference power specifications	1000 W
Slot width
Slot width	2-slot (original 6 GB Founders Edition); 12 GB partner cards vary	2-slot (Founders Edition)
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.	304 × 137 mm, 2-slot (Founders Edition)
Video encode and decode
Video encode and decode	Seventh-generation NVENC, fourth-generation NVDEC (NVIDIA comparison table); no hardware AV1 encode	3 × ninth-generation NVENC, 2 × sixth-generation NVDEC; AV1 encode and decode