audio model · whisper · iOS
Can I run Whisper small on iPad Pro M4 (16GB, 1TB/2TB config)?
Yes. Whisper small runs on iPad Pro M4 (16GB, 1TB/2TB config) at fp16 (whisper.cpp) (~0.85 GB of ~12 GB usable).
Runs at fp16 (whisper.cpp) using ~0.85 GB of ~12 GB usable.
- Peak memory
- ~0.85 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
- Quant
- fp16 (whisper.cpp)
How to run it
Use whisper.cpp or faster-whisper at fp16 (whisper.cpp). It is light enough to run on CPU; a GPU just makes it faster.
- Type
- Speech to text
- Parameters
- 244M
- Peak memory
- ~0.85 GB at fp16 (whisper.cpp)
- License
- MIT
- Memory
- 16 GB unified
- Usable for weights
- ~12 GB
- Power draw
- ~14 W
- Best runtime
- MLX (via Python or Swift; mlx-lm package)
You could also run
Run Whisper small on other hardware
FAQ
Can iPad Pro M4 (16GB, 1TB/2TB config) run Whisper small?
Yes. Whisper small runs on iPad Pro M4 (16GB, 1TB/2TB config) at fp16 (whisper.cpp) (~0.85 GB of ~12 GB usable).
How much memory does Whisper small need?
iPad Pro M4 (16GB, 1TB/2TB config) has room to spare. At fp16 (whisper.cpp) the realistic peak is ~0.85 GB of memory.
What do I use to run Whisper small locally?
Whisper small runs in whisper.cpp or faster-whisper (among others). It runs on CPU, so no GPU is required.
Sources
- apple.com/ipad-pro
- apple.com/newsroom
- developer.apple.com
- enclaveai.app
- github.com/a-ghorbani
- github.com/ggml-org
- github.com/google-ai-edge
- github.com/mainframecomputer
- github.com/openai
- gsmarena.com
- layla-network.ai
- phonearena.com
- privatellm.app
- support.apple.com/en-us/119891
- support.apple.com/en-us/119892
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-08-03. See methodology.