Compare · 3 of 4 products
NVIDIA GeForce RTX 5090vsNVIDIA GeForce RTX 4070 SupervsNVIDIA GeForce RTX 4080 Super
eBay prices refresh hourly — check the listing before you buy. We may earn a commission.
Biggest differences
Memory bandwidth
NVIDIA GeForce RTX 5090 leads
3.56×
higher is better
- NVIDIA GeForce RTX 50901,792 GB/s
- NVIDIA GeForce RTX 4070 Super504 GB/s
- NVIDIA GeForce RTX 4080 Super736 GB/s
Launch price
NVIDIA GeForce RTX 4070 Super leads
3.34×
lower is better
- NVIDIA GeForce RTX 50901,999 USD
- NVIDIA GeForce RTX 4070 Super599 USD
- NVIDIA GeForce RTX 4080 Super999 USD
Shader cores
NVIDIA GeForce RTX 5090 leads
3.04×
higher is better
- NVIDIA GeForce RTX 509021,760 cores
- NVIDIA GeForce RTX 4070 Super7,168 cores
- NVIDIA GeForce RTX 4080 Super10,240 cores
Video memory
NVIDIA GeForce RTX 5090 leads
2.67×
higher is better
- NVIDIA GeForce RTX 509032 GB
- NVIDIA GeForce RTX 4070 Super12 GB
- NVIDIA GeForce RTX 4080 Super16 GB
Where each one wins
NVIDIA GeForce RTX 5090
- Shader cores
- FP32 compute
- Video memory
- Memory type
- Memory bus width
- Memory bandwidth
- Memory speed
- Last-level cache
- PCIe version
- HDMI version
- DisplayPort version
- Video encoders
- Slot width
NVIDIA GeForce RTX 4070 Super
- Launch price
- Board power
- Recommended PSU
NVIDIA GeForce RTX 4080 Super
- Boost clock
- Base clock
What all 3 have
- Power connectors12V-2x6
- HDMI outputs1 ports
- DisplayPort outputs3 ports
- Max displays4 displays
Every spec
Red marks the better value in each row.
Overview
Release date
- 2025-01
- 2024-01
- 2024-01
Launch price
- 1,999 USD
- 599 USD
- 999 USD
Graphics chip
Architecture
- Blackwell
- Ada lovelace
- Ada lovelace
Shader cores
- 21,760 cores
- 7,168 cores
- 10,240 cores
Boost clock
- 2,410 MHz
- 2,475 MHz
- 2,550 MHz
Base clock
- 2,010 MHz
- 1,980 MHz
- 2,290 MHz
FP32 compute
- 104.8 TFLOPS
- 35.5 TFLOPS
- 52 TFLOPS
Memory
Video memory
- 32 GB
- 12 GB
- 16 GB
Memory type
- Gddr7
- Gddr6x
- Gddr6x
Memory bus width
- 512 bit
- 192 bit
- 256 bit
Memory bandwidth
- 1,792 GB/s
- 504 GB/s
- 736 GB/s
Memory speed
- 28 Gbps
- 21 Gbps
- 23 Gbps
Last-level cache
- 96 MB
- 48 MB
- 64 MB
Power
Interface
PCIe version
- 5.0
- 4.0
- 4.0
PCIe lanes
- 16 lanes
- 16 lanes
- Not published
Display outputs
HDMI version
- 2.1b
- 2.1
- 2.1a
DisplayPort version
- 2.1b5
- 1.4a
- 1.4a
HDMI outputs
- 1 ports
- 1 ports
- 1 ports
DisplayPort outputs
- 3 ports
- 3 ports
- 3 ports
Max displays
- 4 displays
- 4 displays
- 4 displays
Video engine
Hardware encode
- H.264, HEVC, AV1
- AV1
- AV1
Video encoders
- 3 encoders
- Not published
- 2 encoders
Size
Card length
- 304 mm
- Not published
- 304 mm
Card height
- 137 mm
- Not published
- 137 mm
Slot width
- 2 slots6
- Not published
- 3 slots
Notes on 6 values — test conditions and caveats
- 1NVIDIA GeForce RTX 5090, Recommended PSU: NVIDIA's minimum for a PC with a Ryzen 9 9950X; it recommends a PCIe CEM 5.1 compliant PSU.
- 2NVIDIA GeForce RTX 4080 Super, Recommended PSU: NVIDIA's 750 W minimum assumes a PC with a Ryzen 9 5900X; needs vary by configuration.
- 3NVIDIA GeForce RTX 4070 Super, Power connectors: Nvidia's 16-pin header is the 12V-2x6 variant; an adapter cable for non-ATX 3.0 power supplies ships with the card.
- 4NVIDIA 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.
- 5NVIDIA GeForce RTX 5090, DisplayPort version: DisplayPort 2.1b at UHBR20 on all three DP outputs.
- 6NVIDIA GeForce RTX 5090, Slot width: The card is 2-slot, but NVIDIA's install guide asks for 3-slot (61 mm) case clearance.
Where to buy
NVIDIA GeForce RTX 5090
NVIDIA GeForce RTX 4070 Super
NVIDIA GeForce RTX 4080 Super








