Skip to content
localmodel.run

audio model · kokoro · iOS

KO Can I run Kokoro-82M on iPad Pro M4 (16GB, 1TB/2TB config)?

Compatibility verdict memory check
Yes, it runsheavy offloading

Yes. Kokoro-82M runs on iPad Pro M4 (16GB, 1TB/2TB config) at fp32 (~1 GB of ~12 GB usable).

Needs ~1 GB Device usable ~12 GB

Runs at fp32 using ~1 GB of ~12 GB usable.

Peak memory
~1 GB
Usable on device
~12 GB
Device memory
16 GB
Quant
fp32

How to run it

Use kokoro (Python) or ONNX Runtime at fp32. It is light enough to run on CPU; a GPU just makes it faster.

Model kokoro
Type
Text to speech
Parameters
82M
Peak memory
~1 GB at fp32
License
Apache-2.0
Full Kokoro-82M 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 Kokoro-82M on other hardware

FAQ

Can iPad Pro M4 (16GB, 1TB/2TB config) run Kokoro-82M?

Yes. Kokoro-82M runs on iPad Pro M4 (16GB, 1TB/2TB config) at fp32 (~1 GB of ~12 GB usable).

How much memory does Kokoro-82M need?

iPad Pro M4 (16GB, 1TB/2TB config) has room to spare. At fp32 the realistic peak is ~1 GB of memory.

What do I use to run Kokoro-82M locally?

Kokoro-82M runs in kokoro (Python) or ONNX Runtime (among others). It runs on CPU, so no GPU is required.

Sources

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