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

rubert-tiny2

by cointegrated

29M params · sentence-similarity · 160 likes · 1.0M downloads

rubert-tiny2 is a 29M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (44692 tok/s), GeForce RTX 5090 (67021 tok/s), M4 Max 128GB (16354 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB44692 tok/scomfortable
GeForce RTX 509032GB67021 tok/scomfortable
M4 Max 128GB128GB16354 tok/scomfortable
M4 Pro 48GB48GB8177 tok/scomfortable
M4 Pro 24GB24GB8177 tok/scomfortable
A100 PCIe 80 GB80GB81882 tok/scomfortable
H100 SXM5 80 GB80GB164691 tok/scomfortable
GeForce RTX 309024GB39514 tok/scomfortable
Radeon RX 7900 XTX24GB32676 tok/scomfortable
GeForce RTX 408016GB31718 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0