# How to run FLUX 3 Image Klein locally

> Updated 2026-10-16 · https://imageklein.com/run-flux-3-image-klein-locally

FLUX 3 Image Klein runs on your own NVIDIA GPU through ComfyUI, Hugging Face Diffusers or Black Forest Labs' reference code. The INT8 build needs as little as 8 GB of VRAM and makes a 1-megapixel image in about 4 seconds on an RTX 5090 and under 9 seconds on an RTX 4070.

## 1. Get access to the weights

- Sign in to Hugging Face and open [black-forest-labs/flux-3-image-klein](https://huggingface.co/black-forest-labs/flux-3-image-klein).
- Accept the FLUX Kommunity License on the page (the repo is gated).
- Pick the checkpoint: **flux-3-image-klein** (distilled, 16 steps — for making images) or **flux-3-image-klein-base** (50 steps — for fine-tuning and LoRA training). ComfyUI users can use **flux-3-image-klein-comfy**.

## 2a. ComfyUI

ComfyUI supports FLUX 3 Image Klein from day one. Update ComfyUI, download the model files from the `flux-3-image-klein-comfy` repo, and load the FLUX 3 Image Klein template. On an 8 GB card, use the **INT8** build — that is the configuration BFL quotes for 8 GB GeForce RTX GPUs.

## 2b. Hugging Face Diffusers

Install Diffusers from source (support landed with the release), then:

```
pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers import ModularPipeline

pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein")
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")

# text-to-image
image = pipe(
    prompt="A wide-angle photo of a red vintage tram on a rainy Lisbon street at dusk, "
           "warm shop lights reflected on wet cobblestones, soft mist, muted palette.",
    generator=torch.Generator().manual_seed(0),
    output="images",
)[0]
image.save("tram.png")

# edit the same image
night = pipe(
    prompt="The same tram on the same street, now at night under heavy snow.",
    image=image,
    generator=torch.Generator().manual_seed(0),
    output="images",
)[0]
night.save("tram_snow.png")
```

The pattern (ModularPipeline, `image=` for edits) follows the official model card; the prompts here are our own.

## 2c. Reference code

Black Forest Labs' GitHub repo [black-forest-labs/flux-3-image-klein](https://github.com/black-forest-labs/flux-3-image-klein) has a CLI (`scripts/cli.py --model distilled`, weights under `weights/`) and a Gradio demo for drawing bounding boxes.

## How much VRAM do you need?

| Setup | GPU memory |
|---|---|
| INT8 build in ComfyUI or Diffusers | as little as 8 GB (GeForce RTX) |
| Reference code, NVFP4, 1024×1024 | ≈25 GB peak |
| Reference code, FP8, 1024×1024 | ≈26 GB peak |
| Reference code, BF16, 1024×1024 | ≈31 GB peak |
| + prompt upsampler | ≈28 GB more |

The reference-code figures are from the model card (measured on a B200). The 8 GB figure is BFL's for the INT8 build on GeForce RTX; BFL hasn't published speed for an 8 GB card or for 4K output.

## How fast is it?

| GPU | Build | 1 MP text-to-image |
|---|---|---|
| RTX 4070 | distilled, INT8 | 8.9 s (edit: 18.9 s) |
| RTX 5090 | distilled, INT8 | 4.1 s (edit: 7.2 s) |
| RTX 5090 | base (50 steps), INT8 | 12.5 s (edit: 27.4 s) |
| DGX Spark | base (50 steps) | 43.8 s |
| GB300 / DGX Station | base (50 steps) | 1.7 s |
| GB300 | distilled, NVFP4 | 0.55 s |

GPU time only (no prompt upsampling), from NVIDIA measurements published by BFL and VentureBeat's reading of the charts. At 2048×2048 an RTX 5090 takes about 15 s and an RTX 4070 about 50 s with the distilled INT8 build.

## Fine-tuning a LoRA

Train on **flux-3-image-klein-base**. Ostris's AI Toolkit and Diffusers support LoRA training from day one, and NVIDIA NeMo AutoModel has recipes that work on the released checkpoints. Serving a LoRA costs about 5% extra generation time.

## FAQ

**Can FLUX 3 Image Klein run on 8 GB VRAM?**
Yes, according to Black Forest Labs: the INT8 build runs on NVIDIA GeForce RTX GPUs with as little as 8 GB of VRAM via ComfyUI or Diffusers. Expect it to be slower than the published RTX 4070/5090 times.

**Can FLUX 3 Image Klein run on a Mac?**
Black Forest Labs only lists NVIDIA hardware and CUDA-based tools at launch. Apple Silicon support depends on the community (for example Diffusers on MPS) and isn't officially documented yet.

**Which checkpoint should I download?**
flux-3-image-klein (distilled, 16 steps, no guidance) to make and edit images; flux-3-image-klein-base (50 steps, guidance 3.5) to fine-tune or train LoRAs.

**Does ComfyUI support FLUX 3 Image Klein?**
Yes, from day one, together with Hugging Face Diffusers, TensorRT-LLM, SGLang Diffusion and vLLM-Omni.


## Sources

- [Hugging Face — black-forest-labs/flux-3-image-klein (model card)](https://huggingface.co/black-forest-labs/flux-3-image-klein)
- [Hugging Face — black-forest-labs/flux-3-image-klein-base](https://huggingface.co/black-forest-labs/flux-3-image-klein-base)
- [GitHub — black-forest-labs/flux-3-image-klein (reference code)](https://github.com/black-forest-labs/flux-3-image-klein)
- [Black Forest Labs — FLUX 3 Image Klein (blog, Oct 15, 2026)](https://bfl.ai/blog/flux-3-image-klein)
- [VentureBeat — FLUX 3 Image Klein weights, free commercial use for smaller businesses](https://venturebeat.com/technology/black-forest-labs-opens-flux-3-image-klein-weights-with-free-commercial-use-limited-to-smaller-businesses)
- [Press release via GlobeNewswire (Oct 15, 2026)](https://www.globenewswire.com/news-release/2026/10/15/3381905/0/en/black-forest-labs-expands-access-to-frontier-visual-intelligence-with-open-weights-release-of-flux-3-image-klein.html)