Qwen

Qwen-Image 2.1

Qwen's image generation and editing model, with RGBA support.text to imageotherNo commercial use253.2K downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 40 GB for inference.

NosanaIn stock · 1 freeStart right away

Nosana network, hosts worldwide

Details

Stock and price checked 16 min ago.

Self-service: you start it yourself, with no order or sales contact.

nvidia-6000-ada

Full price

€0.62

per hour, whole instance, 1 GPU

Research or evaluation use only; commercial use requires a separate license from Qwen.

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Basis
Run the model vLLM-Omni recipe minimum, sized as ceil(33.1 GB weights x 1.2). The recipe reports a measured 34.0 GB peak on one GB300 at 1024x1024 with VAE tiling.	BF16, full	40 GB	Published