Check my GPU

Image models ·

FLUX.2 [klein] 9B

Backbone
9.1B
Native output
1024×1024
Default steps
4
License
flux-non-commercial
Released
2026-01

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/unsloth/FLUX.2-klein-9B-GGUF (opens in a new tab)

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.2-klein-9B (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/flux2 (opens in a new tab)

git clone https://github.com/black-forest-labs/flux2

Links checked 5 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 37.1 GB 20.8 GB 8.8 GB Original weights (opens in a new tab)
FP8 19.9 GB 11.7 GB 5.6 GB Original weights (opens in a new tab)
Q8 GGUF 20.5 GB 12.3 GB 5.8 GB GGUF (opens in a new tab)
Q4 GGUF 16.2 GB 8.0 GB 4.3 GB GGUF (opens in a new tab)

Components

Best hardware for FLUX.2 [klein] 9B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at FP8.

Grade · points Hardware Precision Memory Time per output Fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 15.0/15 Apple M4 Max (64 GB) FP16 37.1 GB / 48.0 GB 11 s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 NVIDIA GeForce RTX 5090 Q8 GGUF 20.5 GB / 32.0 GB 1.7 s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP8 19.9 GB / 24.0 GB 1.8 s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 FP8 19.9 GB / 24.0 GB 3.0 s Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP8 19.9 GB / 24.0 GB 1.6 s Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 15.0/15 Apple M1 Max (64 GB) FP16 37.1 GB / 48.0 GB 16 s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.4/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q8 GGUF 12.3 GB / 16.0 GB 2.9 s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.4/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB Q8 GGUF 12.3 GB / 16.0 GB 5.8 s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.4/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8 GGUF 12.3 GB / 16.0 GB 3.5 s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 37.4/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q8 GGUF 12.3 GB / 16.0 GB 3.1 s Runs well

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.