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

distiluse-base-multilingual-cased-v2

by sentence-transformers

135M params · sentence-similarity · 207 likes · 1.2M downloads

distiluse-base-multilingual-cased-v2 is a 135M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (9745 tok/s), GeForce RTX 5090 (14613 tok/s), M4 Max 128GB (3566 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB9745 tok/scomfortable
GeForce RTX 509032GB14613 tok/scomfortable
M4 Max 128GB128GB3566 tok/scomfortable
M4 Pro 48GB48GB1783 tok/scomfortable
M4 Pro 24GB24GB1783 tok/scomfortable
A100 PCIe 80 GB80GB17854 tok/scomfortable
H100 SXM5 80 GB80GB35910 tok/scomfortable
GeForce RTX 309024GB8616 tok/scomfortable
Radeon RX 7900 XTX24GB7125 tok/scomfortable
GeForce RTX 408016GB6916 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0