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

bge-base-en-v1.5

by BAAI

109M params · feature-extraction · 405 likes · 5.1M downloads

bge-base-en-v1.5 is a 109M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (11992 tok/s), GeForce RTX 5090 (17984 tok/s), M4 Max 128GB (4388 tok/s).

Inference providers

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

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB11992 tok/scomfortable
GeForce RTX 509032GB17984 tok/scomfortable
M4 Max 128GB128GB4388 tok/scomfortable
M4 Pro 48GB48GB2194 tok/scomfortable
M4 Pro 24GB24GB2194 tok/scomfortable
A100 PCIe 80 GB80GB21972 tok/scomfortable
H100 SXM5 80 GB80GB44193 tok/scomfortable
GeForce RTX 309024GB10603 tok/scomfortable
Radeon RX 7900 XTX24GB8768 tok/scomfortable
GeForce RTX 408016GB8511 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0