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

gemma-3-1b-it

by google

1.0B params · text-generation · 870 likes · 3.3M downloads

gemma-3-1b-it is a 1.0B parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (1313 tok/s), GeForce RTX 5090 (1969 tok/s), M4 Max 128GB (480 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB1313 tok/scomfortable
GeForce RTX 509032GB1969 tok/scomfortable
M4 Max 128GB128GB480 tok/scomfortable
M4 Pro 48GB48GB240 tok/scomfortable
M4 Pro 24GB24GB240 tok/scomfortable
A100 PCIe 80 GB80GB2405 tok/scomfortable
H100 SXM5 80 GB80GB4838 tok/scomfortable
GeForce RTX 309024GB1160 tok/scomfortable
Radeon RX 7900 XTX24GB960 tok/scomfortable
GeForce RTX 408016GB931 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0