How fast does Phi-3.5 Mini (GGUF) run on iPhone?
On an iPhone Air (A19, iOS 26.6.1), Phi-3.5 Mini (GGUF) generated 23.2 tokens per second in Pocket AI Lab 1.1.0, averaged over 3 runs of 200 tokens (± 1.2).
On the standard llama-bench style probe it read a 512-token prompt at about 279 tok/s and generated 128 tokens at 14.5 tok/s. Cold load took 0.2 s and the process peaked at 1,739 MB. The phone heated up during this run and decode speed dropped 9% between repetitions, so on a cool phone it can be faster.
How much memory and storage does Phi-3.5 Mini (GGUF) need?
The catalog budgets 2.7 GB of RAM and 2.4 GB of storage for the Q4_K_M build of Phi-3.5 Mini (GGUF). The measured peak footprint on iPhone Air was 1,739 MB.
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 Phi-3.5 Mini (GGUF)?
Phi-3.5 Mini (GGUF) runs on iPhones with 6 GB of RAM or more. On 6 GB phones it fits with little headroom, so long chats may make it reload.
| RAM | iPhones | Pocket AI Lab |
|---|---|---|
| 3–4 GB | iPhone 11, 11 Pro, 12, 12 mini, 13, 13 mini, SE (2nd and 3rd gen) | ✗ Too big |
| 6 GB | iPhone 12 Pro, 13 Pro, 14, 14 Plus, 14 Pro, 15, 15 Plus | ≈ Runs, little headroom |
| 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.
Phi-3.5 Mini (GGUF) is an older model. It stays in the catalog for people who already use it, but the app no longer recommends it.
What can Phi-3.5 Mini (GGUF) do in Pocket AI Lab?
It's a text model for chat, drafting, summaries and quick questions, fully offline once downloaded.
How did Phi-3.5 Mini (GGUF) score on the quality suite?
It passed 78 of 118 tasks, a score of 66.1 out of 100 on suite v3.
Tasks are graded by deterministic checks (exact numbers, regex, word counts, valid JSON), with greedy decoding. See the method.
All runs of Phi-3.5 Mini (GGUF)
| Model | Gen tok/s | pp512 / tg128 | Load s | Peak MB | Score | Date |
|---|---|---|---|---|---|---|
| Phi-3.5 Mini (GGUF) | 23.5 ± 1.2 | ~291 / 20.0 | 0.3 | 1,758 | 76.1 | 2026-09-03 |
| Phi-3.5 Mini (GGUF) | 23.2 ± 1.2 | ~279 / 14.5 | 0.2 | 1,739 | 66.1 | 2026-10-23 |
Other Phi models in the catalog
- Phi-3.5 Mini, MLX, 4bit, 20.7 tok/s (throttled)
How do I install Phi-3.5 Mini (GGUF)?
Open the Models tab in Pocket AI Lab and tap Phi-3.5 Mini (GGUF). The app checks it against your phone's memory, downloads 2.4 GB from Hugging Face and it's ready for offline chat.