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

face-parsing

by jonathandinu

85M params · image-segmentation · 205 likes · 474.4k downloads

face-parsing is a 85M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (15518 tok/s), GeForce RTX 5090 (23271 tok/s), M4 Max 128GB (5678 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB15518 tok/scomfortable
GeForce RTX 509032GB23271 tok/scomfortable
M4 Max 128GB128GB5678 tok/scomfortable
M4 Pro 48GB48GB2839 tok/scomfortable
M4 Pro 24GB24GB2839 tok/scomfortable
A100 PCIe 80 GB80GB28431 tok/scomfortable
H100 SXM5 80 GB80GB57185 tok/scomfortable
GeForce RTX 309024GB13720 tok/scomfortable
Radeon RX 7900 XTX24GB11346 tok/scomfortable
GeForce RTX 408016GB11013 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0