How fast does Whisper base run on iPhone?
Whisper base hasn't been measured on the reference iPhone yet, so there's no speed figure for it here.
You can measure it on your own phone with Model Benchmark in the app. It runs the same protocol as the numbers on the benchmarks page.
How much memory and storage does Whisper base need?
The catalog budgets 800 MB of RAM and 150 MB of storage for the ggml build of Whisper base.
It runs on a memory-mapped backend, so the app checks it against the Metal working set rather than the stricter per-app limit. Weights are read from disk as needed, which keeps the measured footprint low.
Which iPhones can run Whisper base?
Whisper base runs on iPhones with 3–4 GB of RAM or more, which is every iPhone that runs iOS 26.
| RAM | iPhones | Pocket AI Lab |
|---|---|---|
| 3–4 GB | iPhone 11, 11 Pro, 12, 12 mini, 13, 13 mini, SE (2nd and 3rd gen) | ✓ Runs |
| 6 GB | iPhone 12 Pro, 13 Pro, 14, 14 Plus, 14 Pro, 15, 15 Plus | ✓ Runs |
| 8 GB | iPhone 15 Pro, 16, 16 Plus, 16 Pro, 16e, 17, 17e | ✓ Runs |
| 12 GB | iPhone 17 Pro, 17 Pro Max, iPhone Air | ✓ Runs |
Based on the memory budgets the app measures on each class of iPhone (October 2026). Before downloading, the app checks your exact phone and only offers what fits.
What can Whisper base do in Pocket AI Lab?
It transcribes speech. Record a voice message in the chat and Whisper base turns it into text on the phone, then the text goes to whichever chat model you're using.
Other Whisper models in the catalog
- Whisper tiny (English), whisper.cpp, ggml
How do I install Whisper base?
Open the Models tab in Pocket AI Lab and tap Whisper base. The app checks it against your phone's memory, downloads 150 MB from Hugging Face and it's ready for offline chat.