Skip to content
localmodel.run

image model · flux · iOS

FX Can I run FLUX.1 schnell on iPad Pro M4 (16GB, 1TB/2TB config)?

Compatibility verdict VRAM check
Yes, it runsheavy offloading

Yes. FLUX.1 schnell runs on iPad Pro M4 (16GB, 1TB/2TB config) at Q4 GGUF (~6.5 GB of ~12 GB usable).

Needs ~6.5 GB Device usable ~12 GB

Runs at Q4 GGUF using ~6.5 GB of ~12 GB usable.

Peak VRAM
~6.5 GB
Usable on device
~12 GB
Device memory
16 GB
Quant
Q4 GGUF

How to run it

Use ComfyUI or Draw Things at Q4 GGUF. The big text encoder is loaded to encode your prompt, then offloaded before generation, which is why peak VRAM stays near the backbone size rather than the sum of every file.

Model flux
Type
image (DIT)
Parameters
12B
Peak VRAM
~6.5 GB at Q4 GGUF
Resolution
1024×1024
License
Apache-2.0
Full FLUX.1 schnell requirements →
Device iOS
Memory
16 GB unified
Usable for weights
~12 GB
Best runtime
MLX (via Python or Swift; mlx-lm package)
Best models for iPad Pro M4 (16GB, 1TB/2TB config) →

You could also run

Run FLUX.1 schnell on other hardware

FAQ

Can iPad Pro M4 (16GB, 1TB/2TB config) run FLUX.1 schnell?

Yes. FLUX.1 schnell runs on iPad Pro M4 (16GB, 1TB/2TB config) at Q4 GGUF (~6.5 GB of ~12 GB usable).

How much VRAM does FLUX.1 schnell need?

iPad Pro M4 (16GB, 1TB/2TB config) has room to spare. At Q4 GGUF the realistic peak is ~6.5 GB of VRAM, versus ~33 GB with every component kept resident (no offload). With aggressive CPU offload it drops to ~3 GB, much slower.

What do I use to run FLUX.1 schnell locally?

FLUX.1 schnell runs in ComfyUI or Draw Things (among others). It loads as a diffusion checkpoint plus its text encoder and VAE, not a single chat command.

Sources

VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-06-15. See methodology.