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

gpt-neox-20b

by EleutherAI

20.6B params · text-generation · 579 likes · 179.2k downloads

gpt-neox-20b is a 20.6B parameter model. At Q4 quantization it requires 10GB of VRAM. It runs comfortably on GeForce RTX 4090 (63 tok/s), GeForce RTX 5090 (95 tok/s), A100 PCIe 80 GB (116 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB63 tok/scomfortable
GeForce RTX 509032GB95 tok/scomfortable
M4 Max 128GB128GB23 tok/stight
M4 Pro 48GB48GB11 tok/stight
M4 Pro 24GB24GB11 tok/stight
A100 PCIe 80 GB80GB116 tok/scomfortable
H100 SXM5 80 GB80GB234 tok/scomfortable
GeForce RTX 309024GB56 tok/scomfortable
Radeon RX 7900 XTX24GB46 tok/scomfortable
GeForce RTX 408016GB45 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0