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

gemma-4-E4B-it-OBLITERATED

by OBLITERATUS

8.0B params · text-generation · 718 likes · 278.9k downloads

gemma-4-E4B-it-OBLITERATED is a 8.0B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (164 tok/s), GeForce RTX 5090 (246 tok/s), M4 Max 128GB (60 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB164 tok/scomfortable
GeForce RTX 509032GB246 tok/scomfortable
M4 Max 128GB128GB60 tok/scomfortable
M4 Pro 48GB48GB30 tok/scomfortable
M4 Pro 24GB24GB30 tok/scomfortable
A100 PCIe 80 GB80GB300 tok/scomfortable
H100 SXM5 80 GB80GB605 tok/scomfortable
GeForce RTX 309024GB145 tok/scomfortable
Radeon RX 7900 XTX24GB120 tok/scomfortable
GeForce RTX 408016GB116 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0