What GPU do I need to run black-forest-labs/flux-3-image-klein?
5.5B parameters, published in BF16. View on Hugging FaceGated
Set up flux-3-image-kleinflux-3-image-klein is published by black-forest-labs on Hugging Face, with 185,906 downloads and 895 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.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 10.3 GB | 12.4 GB | RTX 3090 | 1 | $0.162/hr |
| FP8 (quantized) | 5.2 GB | 6.2 GB | RTX 4070 | 1 | $0.154/hr |
| INT4 (quantized) | 2.6 GB | 3.1 GB | RTX 3070 | 1 | $0.132/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-3-image-klein at its published (BF16) precision: 1× RTX 3090, at $0.162/hr per GPU ($0.162/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
flux-3-image-klein: common questions
Does flux-3-image-klein fit on a 16 GB GPU?
Yes. At BF16 it needs 12.4 GB of VRAM, so a 16 GB card holds it with 3.6 GB to spare. A 12 GB card is not enough for it at BF16.
Do I need approval to download flux-3-image-klein?
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 12.4 GB the model needs once you have them.
What is the least VRAM flux-3-image-klein can run in?
3.1 GB, at INT4 (quantized), which fits a 6 GB card, against 12.4 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-3-image-klein lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 3090 at $0.162/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.132/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for image-to-image within about a third of flux-3-image-klein's 5.5B parameters, from other model lines.
- FLUX.2-klein-4B (3.9B, BF16)
- Fibo-2.0-edit-turbo (8.1B, BF16)
More on flux-3-image-klein
Fits on a 16 GB GPU at BF16: every model that fits in 16 GB.
Fits on an 8 GB GPU at FP8: every model that fits in 8 GB.
Related reading: RTX 3090 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.
