black-forest-labs

FLUX.2 [klein] 4B

Fast 4B model combining text-to-image, editing and multi-reference generation under Apache 2.0.Apache 2.0Hugging Face

Cheapest GPU in stock that fits

A single GPU with at least 13 GB for inference.

NosanaIn stock · 13 freeStart right away

Nosana network, hosts worldwide

Details

Stock and price checked 7 min ago.

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

nvidia-3090

Full price

€0.17

per hour, whole instance, 1 GPU

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	Setup	Basis
Run the model Model card: fits in about 13 GB VRAM. Card does not state precision; repo weights are BF16.	BF16, full	13 GB	NVIDIA RTX 3090/4070 and above (per model card)	Published
LoRA fine-tuning BFL help center hardware figures for training klein 4B. Precision not stated by source.	BF16, full	12 GB	NVIDIA GPU with 12 GB VRAM, e.g. RTX 3060 12GB, plus 32 GB system RAM	Published