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

Qwen2.5-VL-7B-Instruct

by Qwen

8.3B params · image-text-to-text · 1.5k likes · 4.6M downloads

Qwen2.5-VL-7B-Instruct is a 8.3B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (158 tok/s), GeForce RTX 5090 (237 tok/s), M4 Max 128GB (57 tok/s).

Inference providers

Provider$/1M in$/1M outThroughput
Hyperbolic33 tok/s

GPU compatibility

GPUVRAMQ4 DecodeVerdict
GeForce RTX 409024GB158 tok/scomfortable
GeForce RTX 509032GB237 tok/scomfortable
M4 Max 128GB128GB57 tok/scomfortable
M4 Pro 48GB48GB28 tok/stight
M4 Pro 24GB24GB28 tok/stight
A100 PCIe 80 GB80GB290 tok/scomfortable
H100 SXM5 80 GB80GB583 tok/scomfortable
GeForce RTX 309024GB139 tok/scomfortable
Radeon RX 7900 XTX24GB115 tok/scomfortable
GeForce RTX 408016GB112 tok/scomfortable
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0