RunDiffusion · 6B · Z-Image-Turbo fine-tune
Run Juggernaut Z Fast on iPhone, iPad, and Mac: Photorealistic Portraits
Juggernaut Z Fast is for pictures that pass as real photographs, without the glossy, plastic look common in AI images. Skin shows its pores and lighting behaves like real light, with fewer warped shapes. RunDiffusion tuned it on Alibaba's Z-Image, and it runs on a 12 GB iPhone, an 8 GB iPad, or any Apple Silicon Mac.
- Parameters
- 6B
- License
- Apache License 2.0
- Released
- May 2026
- Download
- 6.29 GB
Juggernaut Z Fast 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.

Juggernaut Z Fast Requirements: Will It Run on My Device?
iPhone
Needs a 12 GB iPhone
iPhone 17 Pro and 17 Pro Max, iPhone 18 Pro and 18 Pro Max, iPhone Air, and iPhone Duo.
iPad
Runs on every supported iPad
Any iPad with an M-series chip.
Takes its time on an 8 GB iPad.
Mac
Runs on any Apple Silicon Mac
M1 or later, from 8 GB of memory up.
Juggernaut Z Fast Specs
Download
- Download Size
- 6.29 GB3.85 GB when the shared text encoder is already installed
- Text Encoder Shared With
- Flux.2 Klein 4B and Z-Image-Turbo
Model
- Maker
- RunDiffusion
- Based On
- Z-Image-Turbo fine-tune
- Parameters
- 6B
- Quantization
- Trained INT4 (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
- 8 (fixed)
- Upscaler
- Off · 2x · 4x
- Negative Prompt
- Yes
- Rewrite Prompt
- Yes
- Output Sizes
- S · 512 pxEvery device
- M · 768 pxEvery device
- L · 1024 px12 GB on iPhone or iPad
- XL · 1536 px24 GB
Juggernaut Z Fast Examples and Prompts
28 of 28 prompts
Archivist examining flood damaged mapsJuggernaut Z Fast
Botanist selfie in greenhouse aisleJuggernaut Z Fast
Brass desk lamp product studyJuggernaut Z Fast
Bride adjusts embroidered cuffs backstageJuggernaut Z Fast
Ceramicist framed by drying shelvesJuggernaut Z Fast
Charred leeks over whipped cheeseJuggernaut Z Fast
Climber chalking hands before ascentJuggernaut Z Fast
Confident stranger in a fogged alleyJuggernaut Z Fast
Couple sharing headphones at sunriseJuggernaut Z Fast
First dance beneath greenhouse lanternsJuggernaut Z Fast
Handheld espresso tamper on marbleJuggernaut Z Fast
Handmade brass tea strainer in balanceJuggernaut Z Fast
Layered rainwear on stone stepsJuggernaut Z Fast
Mirror selfie after pottery classJuggernaut Z Fast
Monochrome tailoring on concrete stepsJuggernaut Z Fast
Night market cleanup after closingJuggernaut Z Fast
Partners knead dough at sunriseJuggernaut Z Fast
Pear tart cooling on parchmentJuggernaut Z Fast
Quiet beekeeper portrait at dawnJuggernaut Z Fast
Rainy tram window travel selfieJuggernaut Z Fast
Rower training at dawn mistJuggernaut Z Fast
Rower training on misty waterJuggernaut Z Fast
Steaming dumplings in bamboo basketJuggernaut Z Fast
Tailor studies a half-finished coatJuggernaut Z Fast
Tailored raincoat in subway breezeJuggernaut Z Fast
Two cyclists pause by the dunesJuggernaut Z Fast
Velvet vow booklets near candlelightJuggernaut Z Fast
Violin maker in workshop lightJuggernaut Z Fast
What Juggernaut Z Fast Is Good At
You will see it most in people: skin with real texture, and light that falls across a face the way it would in a photograph. It wants full, descriptive sentences, and its makers warn that comma-separated keyword lists mostly produce errors and broken concepts. Rewrite Prompt can turn a short description into the kind of sentences it prefers.
Pick It For
- Portraits and people that look photographed, not rendered
- A 4x latent upscaler, up to a 4096-pixel long edge on a 16 GB iPad and 6144 on a 24 GB Mac
- A smaller download once Z-Image-Turbo or Flux.2 Klein 4B is installed, because the three share a text encoder
Know Before You Download
- Fixed at eight steps
- Needs a 12 GB iPhone; the 8 GB iPhones cannot hold it
- Runs on an 8 GB iPad, but takes its time there
Juggernaut Z Fast in Private Diffusion vs. Draw Things vs. ComfyUI
Juggernaut Z Fast 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.
| Feature | Private Diffusion | Draw Things | ComfyUI |
|---|---|---|---|
| Image Quality | Near-lossless: every model is quantization aware distilled (QAD) against the full-size original | Shrinks models after training (post-training palettization) | Runs the weights you load |
| Speed | GPU and Neural Engine together, plus Neural Accelerators on M5, M6, A19 Pro, and A20 Pro | GPU; the Neural Engine only for i8x models on M3 and M4 | PyTorch MPS, the slowest inference framework on Apple platforms |
| Privacy | Collects no data | Privacy label lists Purchases, Identifiers, and User Content | Sends telemetry to PostHog and Datadog, checked by default on first launch |
| Security | App Sandbox and Hardened Runtime | App Sandbox (Mac App Store) | Unsandboxed Electron |
| The App | Native Swift with Liquid Glass, macOS 26.4 or later | Mac Catalyst | Electron |
How to Run Juggernaut Z Fast on iPhone, iPad, and Mac
- Pre-order Private Diffusion on the App Store; it downloads itself on release day.
- Open Downloads in the app and tap Juggernaut Z Fast. It is a single 6.29 GB download with nothing to configure.
- Pick Juggernaut Z Fast in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
Questions About Juggernaut Z Fast
Yes, on an iPhone with 12 GB of memory: the iPhone 17 Pro and 17 Pro Max, the iPhone 18 Pro and 18 Pro Max, the iPhone Air, and the iPhone Duo. Other supported iPhones have 8 GB and cannot hold Juggernaut Z Fast.
6.29 GB, or 3.85 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.
Write it as a photo brief, in full sentences rather than tag lists: any exact on-image text first, then who or what is in the frame, its attributes, the action, the setting, the lighting, and the composition. Name the colors you want. Put anything you do not want in the negative prompt, and leave Rewrite Prompt on when your description is short.
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, Juggernaut Z Fast 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 Juggernaut Z Fast 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 Juggernaut Z Fast 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.