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

Octopus-v2

by NexaAI

2.5B params · text-generation · 890 likes · 350 downloads

Octopus-v2 is a 2.5B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (523 tok/s), GeForce RTX 5090 (785 tok/s), M4 Max 128GB (191 tok/s).

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB523 tok/scomfortable
GeForce RTX 509032GB785 tok/scomfortable
M4 Max 128GB128GB191 tok/scomfortable
M4 Pro 48GB48GB95 tok/scomfortable
M4 Pro 24GB24GB95 tok/scomfortable
A100 PCIe 80 GB80GB959 tok/scomfortable
H100 SXM5 80 GB80GB1930 tok/scomfortable
GeForce RTX 309024GB463 tok/scomfortable
Radeon RX 7900 XTX24GB383 tok/scomfortable
GeForce RTX 408016GB371 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0