Skip to content

Black Forest Labs · 4B · FLUX.2 Klein

Run Flux.2 Klein 4B on iPhone, iPad, and Mac: Fast General-Purpose Images

Flux.2 Klein 4B is a general-purpose model from Black Forest Labs, the team behind FLUX, that turns a plain-sentence prompt into a finished image in four steps. It runs on every iPhone, iPad, and Mac the app supports.

Parameters
4B
License
Apache License 2.0
Released
January 2026
Download
4.94 GB

View on Hugging Face

Flux.2 Klein 4B runs in Private Diffusion, a local AI image generator for iPhone, iPad, and Mac. Every model in the app is trained with quantization aware distillation (QAD) to stay near-lossless at a fraction of its full size. Download it once inside the app.

Pre-order on the App Store
Flux.2 Klein 4B in Private Diffusion Studio on iPhone, with a finished image

Flux.2 Klein 4B Requirements: Will It Run on My Device?

  • iPhone

    Runs on every supported iPhone

    iPhone 15 Pro and later, from 8 GB of memory up.

  • iPad

    Runs on every supported iPad

    Any iPad with an M-series chip.

  • Mac

    Runs on any Apple Silicon Mac

    M1 or later, from 8 GB of memory up.

Check your device

Flux.2 Klein 4B Specs

Download

Download Size
4.94 GB2.51 GB when the shared text encoder is already installed
Text Encoder Shared With
Z-Image-Turbo and Juggernaut Z Fast

Model

Maker
Black Forest Labs
Based On
FLUX.2 Klein
Parameters
4B
Quantization
Trained INT6 (QAD)
License
Apache License 2.0Covers the model itself, not the pictures you make with it. Nothing in it asks anything of your images.

Generation

Steps
4 (fixed)
Upscaler
Off · 1.5x · 2x
Negative Prompt
Yes
Rewrite Prompt
Yes
Output Sizes
  1. S · 512 pxEvery device
  2. M · 768 pxEvery device
  3. L · 1024 pxEvery device
  4. XL · 1536 px16 GB

Flux.2 Klein 4B Examples and Prompts

59 of 59 prompts

Browse Travel prompts

What Flux.2 Klein 4B Is Good At

It is a general-purpose model rather than a specialist, so it suits whatever you want to try first. Black Forest Labs notes that how you phrase a prompt changes how closely it follows it, which is why plain, specific sentences work best.

Some people search for it as Flux 2 Klein; the app lists it as Flux.2 Klein 4B. It is the model we recommend: it runs on every supported device, takes a negative prompt and Rewrite Prompt, and its shared text encoder makes Z-Image-Turbo and Juggernaut Z Fast smaller downloads.

Pick It For

  • Four steps keep the wait short, even on an 8 GB iPhone
  • Negative prompts and on-device prompt rewriting, both on
  • Trying other models next: it shares a text encoder with Z-Image-Turbo and Juggernaut Z Fast, so either of those downloads about 2.4 GB less once it is installed

Know Before You Download

  • Fixed at four steps, with no slider
  • Lettering in the image can come out misspelled or distorted
  • Upscaling tops out at 2x
  • Extra-large output needs a 16 GB device

Flux.2 Klein 4B in Private Diffusion vs. Draw Things vs. ComfyUI

Flux.2 Klein 4B is the same model wherever you run it. The apps differ in how they shrink it to fit, which chips do the work, and who sees your prompts.

Private Diffusion compared with Draw Things and ComfyUI
FeaturePrivate DiffusionDraw ThingsComfyUI
Image QualityNear-lossless: every model is quantization aware distilled (QAD) against the full-size originalShrinks models after training (post-training palettization)Runs the weights you load
SpeedGPU and Neural Engine together, plus Neural Accelerators on M5, M6, A19 Pro, and A20 ProGPU; the Neural Engine only for i8x models on M3 and M4PyTorch MPS, the slowest inference framework on Apple platforms
PrivacyCollects no dataPrivacy label lists Purchases, Identifiers, and User ContentSends telemetry to PostHog and Datadog, checked by default on first launch
SecurityApp Sandbox and Hardened RuntimeApp Sandbox (Mac App Store)Unsandboxed Electron
The AppNative Swift with Liquid Glass, macOS 26.4 or laterMac CatalystElectron

How to Run Flux.2 Klein 4B on iPhone, iPad, and Mac

  1. Pre-order Private Diffusion on the App Store; it downloads itself on release day.
  2. Open Downloads in the app and tap Flux.2 Klein 4B. It is a single 4.94 GB download with nothing to configure.
  3. Pick Flux.2 Klein 4B in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
Pre-order on the App Store

Questions About Flux.2 Klein 4B

  • Yes. Every iPhone from the 15 Pro onward has at least 8 GB of memory, which is what Flux.2 Klein 4B needs, so it runs on every supported iPhone.

  • 4.94 GB, or 2.51 GB when the shared text encoder is already installed. It downloads once inside the app from Private Diffusion's own server and picks up where it left off after an interruption. On iPhone and iPad the download keeps going with the app closed; on a Mac, quitting the app stops it, and it resumes at the next launch. You can delete it to reclaim the space and fetch it again later.

  • Plain sentences work. Describe the subject, the light, and the lens or medium in one or two sentences, and leave Rewrite Prompt on for short prompts: the on-device enhancer expands them before generation runs.

    Build a prompt for Flux.2 Klein 4B part by part

  • Apache License 2.0: Covers the model itself, not the pictures you make with it. Nothing in it asks anything of your images.

  • Yes. After the one-time download, Flux.2 Klein 4B works without a connection. It turns your prompt into a finished image on the device, and you never sign in.

  • It is faster, the pictures hold up better, and nothing leaves your device. Private Diffusion ships Flux.2 Klein 4B quantization aware distilled (QAD), trained against the full-size original, so it stays near-lossless at a fraction of the size. It runs on Apple's own frameworks: the GPU through MLX, including the Neural Accelerators in M5, M6, A19 Pro, and A20 Pro chips, and the Neural Engine through Core ML. ComfyUI runs models through PyTorch's MPS backend, the slowest inference framework on Apple platforms. ComfyUI's desktop app sends usage telemetry to PostHog and error reports to Datadog, with telemetry checked by default on first launch; Private Diffusion collects no data. And Private Diffusion is a sandboxed native Swift app with the hardened runtime on, where ComfyUI's desktop app is an Electron app that is not sandboxed.

  • Private Diffusion ships Flux.2 Klein 4B quantization aware distilled (QAD), trained against the full-size original, so it stays near-lossless; Draw Things shrinks its models after training. It is faster, using the GPU and the Neural Engine together, plus the Neural Accelerators in M5, M6, A19 Pro, and A20 Pro chips. Private Diffusion collects no data, while Draw Things' App Store privacy label lists Purchases, Identifiers, and User Content. And it is a native Swift app built to Apple's Human Interface Guidelines, with Liquid Glass on macOS 26.4 or later, not a Mac Catalyst port.