vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

GeForce RTX 4090 vs GeForce RTX 5080

MetricGeForce RTX 4090GeForce RTX 5080
VRAM24 GB16 GB
Bandwidth1010 GB/s960 GB/s
FP16 TFLOPS82.6 56.3
TDP450 W360 W

Reference model performance computed in browser.

Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0