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

falcon-40b-instruct

by tiiuae

40.0B params · text-generation · 1.2k likes · 40.9k downloads

falcon-40b-instruct is a 40.0B parameter model. At Q4 quantization it requires 20GB of VRAM. It runs comfortably on GeForce RTX 4090 (32 tok/s), GeForce RTX 5090 (49 tok/s), A100 PCIe 80 GB (60 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB32 tok/scomfortable
GeForce RTX 509032GB49 tok/scomfortable
M4 Max 128GB128GB12 tok/stight
M4 Pro 48GB48GB6 tok/stight
M4 Pro 24GB24GB6 tok/stight
A100 PCIe 80 GB80GB60 tok/scomfortable
H100 SXM5 80 GB80GB120 tok/scomfortable
GeForce RTX 309024GB29 tok/stight
Radeon RX 7900 XTX24GB24 tok/stight
M4 Max 64GB64GB12 tok/stight
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0