audio model · kokoro · iOS
Can I run Kokoro-82M on iPhone 16?
Yes. Kokoro-82M runs on iPhone 16 at fp32 (~1 GB of ~4.5 GB usable).
Runs at fp32 using ~1 GB of ~4.5 GB usable.
- Peak memory
- ~1 GB
- Usable on device
- ~4.5 GB
- Device memory
- 8 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.
- Type
- Text to speech
- Parameters
- 82M
- Peak memory
- ~1 GB at fp32
- License
- Apache-2.0
- Memory
- 8 GB unified
- Usable for weights
- ~4.5 GB
- Power draw
- ~11 W
- Best runtime
- llama.cpp + Metal (via PocketPal or Off Grid app)
You could also run
Run Kokoro-82M on other hardware
FAQ
Can iPhone 16 run Kokoro-82M?
Yes. Kokoro-82M runs on iPhone 16 at fp32 (~1 GB of ~4.5 GB usable).
How much memory does Kokoro-82M need?
iPhone 16 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
- apple.com
- developer.apple.com
- en.wikipedia.org/wiki/Apple_A18
- en.wikipedia.org/wiki/IPhone_16
- enclaveai.app
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mainframecomputer
- github.com/puff-dayo
- github.com/remsky
- gsmarena.com
- huggingface.co/FluidInference
- huggingface.co/hexgrad
- layla-network.ai
- macrumors.com
- privatellm.app
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-08-03. See methodology.