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

EuroLLM-22B-Instruct-2512

by utter-project

22.6B params · text-generation · 59 likes · 3.8k downloads

EuroLLM-22B-Instruct-2512 is a 22.6B parameter model. At Q4 quantization it requires 11GB of VRAM. It runs comfortably on GeForce RTX 4090 (58 tok/s), GeForce RTX 5090 (86 tok/s), A100 PCIe 80 GB (106 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Public AI

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB58 tok/scomfortable
GeForce RTX 509032GB86 tok/scomfortable
M4 Max 128GB128GB21 tok/stight
M4 Pro 48GB48GB10 tok/stight
M4 Pro 24GB24GB10 tok/stight
A100 PCIe 80 GB80GB106 tok/scomfortable
H100 SXM5 80 GB80GB213 tok/scomfortable
GeForce RTX 309024GB51 tok/scomfortable
Radeon RX 7900 XTX24GB42 tok/scomfortable
GeForce RTX 408016GB41 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0