NVIDIA GeForce RTX 3090 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

GeForce RTX 3090 compared with GeForce RTX 4080

	NVIDIAGeForce RTX 3090	NVIDIAGeForce RTX 4080
Overview
Released
Released	September 2020	November 2022
Performance
Chip maker
Chip maker	NVIDIA	NVIDIA
Architecture
Architecture	Ampere	Ada Lovelace
Shader cores
Shader cores	10,496	9,728
Boost clock
Boost clock	1,700 MHz	2,510 MHz (better)
Architecture
Architecture	GA102; 82 Streaming Multiprocessors. Specifications describe NVIDIA's reference card; the photo shows PNY's stock-clock XLR8 Gaming UPRISING EPIC-X RGB Triple Fan, whose cooler and dimensions differ.	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	Samsung 8 nm 8N NVIDIA custom process; 28.3 billion transistors; 628.4 mm² die	TSMC 4N; 45.9 billion transistors; 378.6 mm² die
Ray tracing
Ray tracing	82 second-generation RT Cores	76 third-generation RT Cores; 113 RT TFLOPS
AI cores
AI cores	328 third-generation Tensor Cores	304 fourth-generation Tensor Cores; 780 AI TOPS
Upscaling and frame generation
Upscaling and frame generation	NVIDIA DLSS upscaling; no DLSS Frame Generation	DLSS 3.5 with Super Resolution, DLAA, Ray Reconstruction and Frame Generation
Base clock
Base clock	1.40 GHz on NVIDIA's current page; PNY's stock-clock card lists 1,395 MHz base and 1,695 MHz boost, matching the NVIDIA whitepaper's boost rather than the current rounded 1.70 GHz	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	6,144 KB L2	65,536 KB L2
Memory
Video memory
Video memory	24 GB GDDR6X (better)	16 GB GDDR6X
Memory bus
Memory bus	384-bit (better)	256-bit
Memory bandwidth
Memory bandwidth	936 GB/s (better)	716.8 GB/s
Memory detail
Memory detail	19.5 Gbps GDDR6X	22.4 Gbps GDDR6X
Connections and power
Board power
Board power	350 W	320 W (better)
Interface
Interface	PCIe 4.0	PCIe 4.0
Display outputs
Display outputs	3 × DisplayPort 1.4a, 1 × HDMI 2.1; up to 4 displays; HDCP 2.3; NVLink supported	3 × DisplayPort 1.4a, 1 × HDMI 2.1a; up to 4 displays; HDCP 2.3
Maximum resolution
Maximum resolution	7680 × 4320; HDMI supports 4K 120 Hz HDR or 8K 60 Hz HDR	4K at 240 Hz or 8K at 60 Hz with DSC and HDR
Power connector
Power connector	2 × PCIe 8-pin cables through the included adapter to 1 × 12-pin (Founders Edition)	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, based on NVIDIA's Intel Core i9-10900K test system	750 W; NVIDIA recommends another 36 mm of clearance for the power cable
Slot width
Slot width	3-slot (Founders Edition)	3-slot (Founders Edition)
Size (reference card)
Size (reference card)	313 × 138 mm, 3-slot (Founders Edition); allow another 35 mm for the included power adapter	304 × 137 mm, 3-slot; NVIDIA's system-clearance guide specifies 61 mm thickness (Founders Edition)
Video encode and decode
Video encode and decode	Seventh-generation NVENC, fifth-generation NVDEC; hardware AV1 decode, no AV1 encode	2 × eighth-generation NVENC, fifth-generation NVDEC; AV1 encode and decode