NVIDIA GeForce RTX 5070: Specs, Key Features & Rivals
The RTX 5070 is a card from NVIDIA in the upper-midrange graphics card class. Below, you’ll find its full specs and how it compares. The competition for the RTX 5070 includes RX 9070, RX 9070 XT and RTX 4070 Super.
FP32 computeTheoretical peak; AMD counts dual-issue, so compare within a brand only
30.9 TFLOPS
Memory
Memory: NVIDIA GeForce RTX 5070
VRAM
12 GB
Memory type
GDDR7
Memory bus
192-bit
Memory bandwidth
672 GB/s
Features
Features: NVIDIA GeForce RTX 5070
Upscaling
DLSS 4 Super Resolution
Frame generation
DLSS 4 Multi Frame Generation (up to 4x)
PCIe interface
PCIe 5.0 x16
Power & Thermals
Power & Thermals: NVIDIA GeForce RTX 5070
Total board power
250 W
Recommended PSU
650 W
Power connector
1x 16-pin (12V-2x6)
Size & Connectivity
Size & Connectivity: NVIDIA GeForce RTX 5070
Reference card length
9.53 in
Slot width
2 slots
Display outputs
3x DisplayPort 2.1b, 1x HDMI 2.1b
Price
Price: NVIDIA GeForce RTX 5070
Launch price (MSRP)
$549
How It Stacks Up in the Upper-Midrange Graphics Card Class
On shader units, the RTX 5070 exceeds the class average by 5.2% in raw numbers. On fp32 compute, the RTX 5070 sits right around the average for its class. The RTX 5070 is close to its class average for vram.
