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

albert-base-v2

by albert

12M params · fill-mask · 140 likes · 462.6k downloads

albert-base-v2 is a 12M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (110873 tok/s), GeForce RTX 5090 (166268 tok/s), M4 Max 128GB (40573 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB110873 tok/scomfortable
GeForce RTX 509032GB166268 tok/scomfortable
M4 Max 128GB128GB40573 tok/scomfortable
M4 Pro 48GB48GB20286 tok/scomfortable
M4 Pro 24GB24GB20286 tok/scomfortable
A100 PCIe 80 GB80GB203136 tok/scomfortable
H100 SXM5 80 GB80GB408570 tok/scomfortable
GeForce RTX 309024GB98029 tok/scomfortable
Radeon RX 7900 XTX24GB81065 tok/scomfortable
GeForce RTX 408016GB78687 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0