What GPU do I need to run black-forest-labs/FLUX.2-dev?
A 32.2B-parameter text-to-image model. 32.2B parameters, published in BF16. View on Hugging FaceGated
FLUX.2-dev is published by black-forest-labs on Hugging Face, with 608,892 downloads and 2,139 likes to date. It's a unlisted-architecture model built for image-to-image, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
What FLUX.2-dev is
FLUX.2-dev is a 32.2B-parameter text-to-image model published by Black Forest Labs on Hugging Face, released under Custom license.
License note: a lab-specific license (tagged "other" on Hugging Face); read the model card's own license section before commercial use. Facts in this section are sourced from FLUX.2-dev's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Text-to-image generation
- Creative asset generation
- ComfyUI workflows
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 60.0 GB | 72.0 GB | A100 | 1 | $1.21/hr |
| cheaper alt. | RTX 5060 Ti | 5 | $0.550/hr | ||
| FP8 (quantized) | 30.0 GB | 36.0 GB | RTX 4090 | 1 | $0.485/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.330/hr | ||
| INT4 (quantized) | 15.0 GB | 18.0 GB | RTX A5000 | 1 | $0.176/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run FLUX.2-dev at its published (BF16) precision: 1× A100, at $1.21/hr per GPU ($1.21/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
FLUX.2-dev: common questions
Can FLUX.2-dev run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 72.0 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.21/hr.
Do I need approval to download FLUX.2-dev?
Yes. black-forest-labs gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 72.0 GB the model needs once you have them.
What is the least VRAM FLUX.2-dev can run in?
18.0 GB, at INT4 (quantized), which fits a 24 GB card, against 72.0 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing FLUX.2-dev lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.21/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.
How to run FLUX.2-dev
Run FLUX.2-dev with Diffusers (Python)
Generic example using Hugging Face's diffusers library, not from the model's own docs.
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-dev", torch_dtype=torch.bfloat16)
pipe.to("cuda")
image = pipe("a description of the scene").images[0]
image.save("output.png")Run FLUX.2-dev with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download black-forest-labs/FLUX.2-dev's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.
Deploy FLUX.2-dev on Aquanode
Aquanode has no one-click deploy template for FLUX.2-dev; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch the ComfyUI template sized to the requirement above (1× A100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch the ComfyUI templateWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More FLUX.2 models
- FLUX.2-klein-9B (9.1B, BF16)
- flux2-klein-9b-uncensored-text-encoder (8.2B, F16)
- FLUX.2-klein-4B (3.9B, BF16)
- FLUX.2-klein-base-4B (3.9B, BF16)
Related reading: A100 pricing and specs, and The best GPUs for AI, ranked.
