Check my GPU

Image models ·

FLUX.1 Fill [dev]

Backbone
11.9B
Native output
1024×1024
Default steps
28
License
flux-1-dev-non-commercial
Released
2024-11

How to run it

Original weights · Hugging Face

Full-precision files from Black Forest Labs, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/black-forest-labs/FLUX.1-Fill-dev (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

Reference code, inference scripts and docs from Black Forest Labs. The weights themselves download from Hugging Face.

github.com/black-forest-labs/flux (opens in a new tab)

git clone https://github.com/black-forest-labs/flux

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 36.4 GB 26.6 GB 11.0 GB Original weights (opens in a new tab)
FP8 19.6 GB 14.7 GB 6.8 GB Original weights (opens in a new tab)

Components

Best hardware for FLUX.1 Fill [dev]

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A580 (launch price $179) at FP8.

Grade · points Hardware Precision Memory Time per output Fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP8 19.6 GB / 24.0 GB 11 s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.1/15 NVIDIA GeForce RTX 5090 FP8 19.6 GB / 32.0 GB 9.4 s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP8 19.6 GB / 24.0 GB 13 s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 10.3/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 FP8 19.6 GB / 24.0 GB 21 s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.7/15 NVIDIA RTX PRO 6000 Blackwell FP16 36.4 GB / 96.0 GB 9.2 s Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 5.5/15, Memory use 15.0/15 Apple M4 Max (64 GB) FP16 36.4 GB / 48.0 GB 73 s Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15 Apple M1 Max (64 GB) FP16 36.4 GB / 48.0 GB 1.9 min Runs well
78 ptsGreat (A) · 78 of 100 points: Model quality 33.5/45, Memory fit 18.0/25, Speed 12.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT FP8 14.7 GB / 16.0 GB 16 s Tight fit
78 ptsGreat (A) · 78 of 100 points: Model quality 33.5/45, Memory fit 18.0/25, Speed 12.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 FP8 14.7 GB / 16.0 GB 16 s Tight fit
78 ptsGreat (A) · 78 of 100 points: Model quality 33.5/45, Memory fit 18.0/25, Speed 11.6/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER FP8 14.7 GB / 16.0 GB 17 s Tight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.