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

bitnet-b1.58-2B-4T

by microsoft

850M params · text-generation · 1.5k likes · 9.9k downloads

bitnet-b1.58-2B-4T is a 850M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (1545 tok/s), GeForce RTX 5090 (2317 tok/s), M4 Max 128GB (565 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB1545 tok/scomfortable
GeForce RTX 509032GB2317 tok/scomfortable
M4 Max 128GB128GB565 tok/scomfortable
M4 Pro 48GB48GB282 tok/scomfortable
M4 Pro 24GB24GB282 tok/scomfortable
A100 PCIe 80 GB80GB2830 tok/scomfortable
H100 SXM5 80 GB80GB5693 tok/scomfortable
GeForce RTX 309024GB1366 tok/scomfortable
Radeon RX 7900 XTX24GB1129 tok/scomfortable
GeForce RTX 408016GB1096 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0