Compare · 3 of 4 products
NVIDIA GeForce RTX 5060vsNVIDIA GeForce RTX 5080vsNVIDIA GeForce RTX 4080 Super
eBay prices refresh hourly — check the listing before you buy. We may earn a commission.
Biggest differences
Launch price
NVIDIA GeForce RTX 5060 leads
3.34×
lower is better
- NVIDIA GeForce RTX 5060299 USD
- NVIDIA GeForce RTX 5080999 USD
- NVIDIA GeForce RTX 4080 Super999 USD
Shader cores
NVIDIA GeForce RTX 5080 leads
2.8×
higher is better
- NVIDIA GeForce RTX 50603,840 cores
- NVIDIA GeForce RTX 508010,752 cores
- NVIDIA GeForce RTX 4080 Super10,240 cores
Board power
NVIDIA GeForce RTX 5060 leads
2.48×
lower is better
- NVIDIA GeForce RTX 5060145 W
- NVIDIA GeForce RTX 5080360 W
- NVIDIA GeForce RTX 4080 Super320 W
Memory bandwidth
NVIDIA GeForce RTX 5080 leads
2.14×
higher is better
- NVIDIA GeForce RTX 5060448 GB/s
- NVIDIA GeForce RTX 5080960 GB/s
- NVIDIA GeForce RTX 4080 Super736 GB/s
Where each one wins
NVIDIA GeForce RTX 5060
- Launch price
- Memory type
- Board power
- Recommended PSU
- PCIe version
- HDMI version
- DisplayPort version
NVIDIA GeForce RTX 5080
- Shader cores
- Boost clock
- Base clock
- FP32 compute
- Video memory
- Memory type
- Memory bus width
- Memory bandwidth
- Memory speed
- PCIe version
- PCIe lanes
- HDMI version
- DisplayPort version
- Video encoders
- Slot width
NVIDIA GeForce RTX 4080 Super
- Video memory
- Memory bus width
- Video encoders
What all 3 have
- HDMI outputs1 ports
- DisplayPort outputs3 ports
- Max displays4 displays
Every spec
Red marks the better value in each row.
Overview
Release date
- 2025-05
- 2025-01
- 2024-01
Launch price
- 299 USD
- 999 USD
- 999 USD
Graphics chip
Architecture
- Blackwell
- Blackwell
- Ada lovelace
Shader cores
- 3,840 cores
- 10,752 cores
- 10,240 cores
Boost clock
- 2,500 MHz
- 2,620 MHz
- 2,550 MHz
Base clock
- 2,280 MHz
- 2,300 MHz
- 2,290 MHz
FP32 compute
- 19.2 TFLOPS
- 56.3 TFLOPS
- 52 TFLOPS
Memory
Video memory
- 8 GB
- 16 GB
- 16 GB
Memory type
- Gddr7
- Gddr7
- Gddr6x
Memory bus width
- 128 bit
- 256 bit
- 256 bit
Memory bandwidth
- 448 GB/s
- 960 GB/s
- 736 GB/s
Memory speed
- 28 Gbps
- 30 Gbps
- 23 Gbps
Last-level cache
- Not published
- 64 MB
- 64 MB
Power
Interface
PCIe version
- 5.0
- 5.0
- 4.0
PCIe lanes
- 8 lanes
- 16 lanes
- Not published
Display outputs
Video engine
Hardware encode
- AV1
- H.264, HEVC, AV1
- AV1
Video encoders
- 1 encoders
- 2 encoders
- 2 encoders
Size
Card length
- Not published
- 304 mm
- 304 mm
Card height
- Not published
- 137 mm
- 137 mm
Slot width
- Not published
- 2 slots8
- 3 slots
Notes on 8 values — test conditions and caveats
- 1NVIDIA GeForce RTX 5060, Recommended PSU: NVIDIA's 550 W minimum assumes a PC with a Ryzen 9 9950X; power needs vary by system configuration.
- 2NVIDIA GeForce RTX 5080, Recommended PSU: NVIDIA's minimum for a PC with a Ryzen 9 9950X; it recommends a PCIe CEM 5.1 compliant PSU.
- 3NVIDIA GeForce RTX 4080 Super, Recommended PSU: NVIDIA's 750 W minimum assumes a PC with a Ryzen 9 5900X; needs vary by configuration.
- 4NVIDIA GeForce RTX 5060, Power connectors: The card takes one 8-pin; a 300 W or greater Gen 5 (16-pin) PSU cable can be used with the in-box adapter.
- 5NVIDIA GeForce RTX 4080 Super, Power connectors: Card takes a 16-pin 12V-2x6 connector; a 3x PCIe 8-pin adapter ships in the box for PSUs without a PCIe Gen 5 cable.
- 6NVIDIA GeForce RTX 5060, DisplayPort version: DisplayPort 2.1b outputs run at the UHBR20 link rate per NVIDIA's footnote.
- 7NVIDIA GeForce RTX 5080, DisplayPort version: DisplayPort 2.1b at UHBR20 on all three DP outputs.
- 8NVIDIA GeForce RTX 5080, Slot width: The card is 2-slot (40 mm thick), but NVIDIA's install guide asks for 3-slot (61 mm) case clearance.
Where to buy
NVIDIA GeForce RTX 5060
NVIDIA GeForce RTX 5080
NVIDIA GeForce RTX 4080 Super








