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

paraphrase-multilingual-MiniLM-L12-v2

by sentence-transformers

118M params · sentence-similarity · 1.2k likes · 23.1M downloads

paraphrase-multilingual-MiniLM-L12-v2 is a 118M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (11159 tok/s), GeForce RTX 5090 (16735 tok/s), M4 Max 128GB (4083 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB11159 tok/scomfortable
GeForce RTX 509032GB16735 tok/scomfortable
M4 Max 128GB128GB4083 tok/scomfortable
M4 Pro 48GB48GB2041 tok/scomfortable
M4 Pro 24GB24GB2041 tok/scomfortable
A100 PCIe 80 GB80GB20446 tok/scomfortable
H100 SXM5 80 GB80GB41123 tok/scomfortable
GeForce RTX 309024GB9866 tok/scomfortable
Radeon RX 7900 XTX24GB8159 tok/scomfortable
GeForce RTX 408016GB7920 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0