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

vit-base-patch16-224

by google

87M params · image-classification · 940 likes · 4.1M downloads

vit-base-patch16-224 is a 87M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (15167 tok/s), GeForce RTX 5090 (22745 tok/s), M4 Max 128GB (5550 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
HF Inference

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB15167 tok/scomfortable
GeForce RTX 509032GB22745 tok/scomfortable
M4 Max 128GB128GB5550 tok/scomfortable
M4 Pro 48GB48GB2775 tok/scomfortable
M4 Pro 24GB24GB2775 tok/scomfortable
A100 PCIe 80 GB80GB27788 tok/scomfortable
H100 SXM5 80 GB80GB55891 tok/scomfortable
GeForce RTX 309024GB13410 tok/scomfortable
Radeon RX 7900 XTX24GB11089 tok/scomfortable
GeForce RTX 408016GB10764 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0