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

bert-base-cased

by google-bert

109M params · fill-mask · 350 likes · 3.3M downloads

bert-base-cased is a 109M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (12053 tok/s), GeForce RTX 5090 (18075 tok/s), M4 Max 128GB (4410 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB12053 tok/scomfortable
GeForce RTX 509032GB18075 tok/scomfortable
M4 Max 128GB128GB4410 tok/scomfortable
M4 Pro 48GB48GB2205 tok/scomfortable
M4 Pro 24GB24GB2205 tok/scomfortable
A100 PCIe 80 GB80GB22083 tok/scomfortable
H100 SXM5 80 GB80GB44416 tok/scomfortable
GeForce RTX 309024GB10656 tok/scomfortable
Radeon RX 7900 XTX24GB8812 tok/scomfortable
GeForce RTX 408016GB8554 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0