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

bert-base-multilingual-uncased-sentiment

by nlptown

167M params · text-classification · 465 likes · 1.3M downloads

bert-base-multilingual-uncased-sentiment is a 167M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (7845 tok/s), GeForce RTX 5090 (11765 tok/s), M4 Max 128GB (2870 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB7845 tok/scomfortable
GeForce RTX 509032GB11765 tok/scomfortable
M4 Max 128GB128GB2870 tok/scomfortable
M4 Pro 48GB48GB1435 tok/scomfortable
M4 Pro 24GB24GB1435 tok/scomfortable
A100 PCIe 80 GB80GB14373 tok/scomfortable
H100 SXM5 80 GB80GB28910 tok/scomfortable
GeForce RTX 309024GB6936 tok/scomfortable
Radeon RX 7900 XTX24GB5736 tok/scomfortable
GeForce RTX 408016GB5567 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0