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

segformer-b0-finetuned-ade-512-512

by nvidia

4M params · image-segmentation · 183 likes · 474.9k downloads

segformer-b0-finetuned-ade-512-512 is a 4M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (349834 tok/s), GeForce RTX 5090 (524618 tok/s), M4 Max 128GB (128018 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB349834 tok/scomfortable
GeForce RTX 509032GB524618 tok/scomfortable
M4 Max 128GB128GB128018 tok/scomfortable
M4 Pro 48GB48GB64009 tok/scomfortable
M4 Pro 24GB24GB64009 tok/scomfortable
A100 PCIe 80 GB80GB640945 tok/scomfortable
H100 SXM5 80 GB80GB1289137 tok/scomfortable
GeForce RTX 309024GB309305 tok/scomfortable
Radeon RX 7900 XTX24GB255781 tok/scomfortable
GeForce RTX 408016GB248278 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0