On an Apple Silicon Mac, a documented way to run FLUX locally is Argmax DiffusionKit, which uses MLX. Create an isolated Conda environment, install DiffusionKit, then generate an image from the command line. The guide below covers that Mac-oriented route, an alternative setup from Black Forest Labs (BFL), and the practical differences between FLUX.1 schnell and FLUX.1 dev.
How do I install Flux on a Mac?
For the Apple Silicon MLX route, Argmax documents installing DiffusionKit inside a dedicated Conda environment. This keeps its Python packages separate from other projects. The project describes itself as an Apple Silicon Core ML/MLX implementation; the commands below use its Conda and pip setup. Argmax DiffusionKit documentation
As an Amazon Associate I earn from qualifying purchases.
-
Create and activate the environment:
conda create -n diffusionkit python=3.11 -y conda activate diffusionkit -
Install the package:
pip install diffusionkit
This is a specifically documented Apple Silicon path, not a guarantee of equivalent support or performance on every Mac. The cited project documentation does not establish a universal minimum unified-memory requirement or a reliable generation time across Mac models.
Free tools Windows power users keep installed
One-click scans. No signup required.
How do I run Flux locally on a Mac?
Once DiffusionKit is installed and the environment is active, run the documented example from Terminal:
#1 Best Overall
- SUPERCHARGED BY M5 — The 14-inch MacBook Pro with M5 brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. Featuring all-day battery life and a breathtaking Liquid Retina XDR display with up to 1600 nits peak brightness, it’s pro in every way.*
- HAPPILY EVER FASTER — Along with its faster CPU and unified memory, M5 features a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR APPLE INTELLIGENCE — Apple Intelligence is the personal intelligence system that helps you write, express yourself, and get things done effortlessly. With groundbreaking privacy protections, it gives you peace of mind that no one else can access your data — not even Apple.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.
- APPS FLY WITH APPLE SILICON — All your favorites, including Microsoft 365 and Adobe Creative Cloud, run lightning fast in macOS.*
diffusionkit-cli --prompt "a photo of a cat" --output-path ./cat.pngThe command asks the CLI to save the generated image as cat.png in the current directory. The documentation also lists options including --seed, --height, and --width. To see the flags available in the version you installed, run:
diffusionkit-cli -hCLI switches can change between package versions, so use the installed help output if an option in an older example is not recognized. Argmax DiffusionKit FLUX model documentation
Generate images from Python with DiffusionKit
DiffusionKit also documents a Python pipeline. This example uses FLUX.1 schnell, a 512-by-512 output, and four generation steps:
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchRank #2
- FAST RUNS IN THE FAMILY — The 16-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
- BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
- MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.
from diffusionkit.mlx import FluxPipeline
HEIGHT = 512
WIDTH = 512
pipeline = FluxPipeline(
shift=1.0,
model_version="argmaxinc/mlx-FLUX.1-schnell",
low_memory_mode=True,
a16=True,
w16=True,
)
image = pipeline.generate_image(
"a photo of a cat",
cfg_weight=0.,
num_steps=4,
latent_size=(HEIGHT // 8, WIDTH // 8),
)
image.save("cat.png")For dev, select the dev model version documented by DiffusionKit and use the example’s 50 steps instead of schnell’s four. These are project example settings, not measured Mac generation times or a controlled comparison of output quality. Consult the DiffusionKit project documentation for its current pipeline details.
Alternative: use the Black Forest Labs repository
BFL publishes a general Python installation and sampling route. It is separate from the Apple Silicon MLX setup above: the repository demo defaults to CUDA when available and otherwise CPU, so its commands should not be treated as an Apple Silicon-optimized recipe. Black Forest Labs FLUX repository
-
Clone the official repository and enter its directory:
Rank #3
Sale
Apple 2026 MacBook Pro Laptop with Apple M5 Pro chip with 18-core CPU and 20-core GPU: Built for AI, 16.2-inch Liquid Retina XDR Display, 48GB Unified Memory, 1TB SSD, Wi-Fi 7; Space Black- FAST RUNS IN THE FAMILY — The 16-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
- BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
- MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.
git clone https://github.com/black-forest-labs/flux.git cd flux -
Create and activate a Python 3.10 virtual environment:
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.python3.10 -m venv .venv source .venv/bin/activate -
Install the repository and its optional dependencies:
pip install -e ".[all]" -
Run the local text-to-image command for the model you want:
Rank #4
Sale
Apple 2025 MacBook Pro Laptop with Apple M5 chip with 10‑core CPU and 10‑core GPU: Built for AI, 14.2-inch Liquid Retina XDR Display, 24GB Unified Memory, 1TB SSD Storage; Space Black- SUPERCHARGED BY M5 — The 14-inch MacBook Pro with M5 brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. Featuring all-day battery life and a breathtaking Liquid Retina XDR display with up to 1600 nits peak brightness, it’s pro in every way.*
- HAPPILY EVER FASTER — Along with its faster CPU and unified memory, M5 features a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR APPLE INTELLIGENCE — Apple Intelligence is the personal intelligence system that helps you write, express yourself, and get things done effortlessly. With groundbreaking privacy protections, it gives you peace of mind that no one else can access your data — not even Apple.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.
- APPS FLY WITH APPLE SILICON — All your favorites, including Microsoft 365 and Adobe Creative Cloud, run lightning fast in macOS.*
python -m flux t2i --name flux-schnell --loop python -m flux t2i --name flux-dev --loop
The repository says model weights are downloaded from Hugging Face when a demo starts. If you have local weight files, it documents FLUX_MODEL and FLUX_AE as environment variables for supplying model and autoencoder paths. BFL repository README
FLUX.1 schnell vs. FLUX.1 dev
Both model cards describe 12-billion-parameter models, but their training approaches, documented step settings, and licenses differ. The step counts below come from project examples or the model card; they do not establish actual speed or a visual quality ranking on a Mac.
| Comparison | FLUX.1 schnell | FLUX.1 dev |
|---|---|---|
| Model size | 12 billion parameters, per the BFL model card | 12 billion parameters, per the BFL model card |
| Documented generation steps | Model card says one to four steps; DiffusionKit’s example uses four | DiffusionKit’s example uses 50; BFL’s Diffusers example also shows 50 |
| Distillation | Latent adversarial diffusion distillation, per the model card | Guidance distillation, per the model card |
| License | Apache 2.0 | FLUX.1-dev Non-Commercial License; the model page requires accepting its access conditions |
| Practical distinction | A low-step option when minimizing iteration count is the priority | A non-schnell comparison point; the example’s larger step count does not establish how fast it will run on a particular Mac |
Sources for the model properties and licenses: FLUX.1 schnell model card, FLUX.1 dev model card, and DiffusionKit examples.
Best Value
- SUPERCHARGED BY M5 — The 14-inch MacBook Pro with M5 brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. Featuring all-day battery life and a breathtaking Liquid Retina XDR display with up to 1600 nits peak brightness, it’s pro in every way.*
- HAPPILY EVER FASTER — Along with its faster CPU and unified memory, M5 features a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR APPLE INTELLIGENCE — Apple Intelligence is the personal intelligence system that helps you write, express yourself, and get things done effortlessly. With groundbreaking privacy protections, it gives you peace of mind that no one else can access your data — not even Apple.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.
- APPS FLY WITH APPLE SILICON — All your favorites, including Microsoft 365 and Adobe Creative Cloud, run lightning fast in macOS.*
For commercial use, check the license for the specific model before proceeding. Running a model locally does not override its license; schnell’s Apache 2.0 terms differ from dev’s non-commercial terms. The dev model page also has access conditions that users must accept.
What the published Mac guidance does not establish
-
A universal minimum memory requirement: the cited official and project documentation does not state a dependable minimum unified-memory figure for all Apple Silicon Macs.
-
Generation speed on your Mac: example step counts are not a benchmark. Results may depend on the Mac and software configuration, and the cited sources provide no comparable per-image timing.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteSpecial offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy. -
A visual winner between the two models: the cited model and project documentation does not prove that either build produces better-looking results on Mac hardware.
Quick Recap
SaleBestseller No. 1SaleBestseller No. 2SaleBestseller No. 3SaleBestseller No. 4
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
