How fast does Llama 3.2 3B (GGUF) run on iPhone?
On an iPhone Air (A19, iOS 26.6.1), Llama 3.2 3B (GGUF) generated 26.9 tokens per second in Pocket AI Lab 1.1.0, averaged over 3 runs of 200 tokens (± 0.6).
On the standard llama-bench style probe it read a 512-token prompt at about 459 tok/s and generated 128 tokens at 21.9 tok/s. Cold load took 0.2 s and the process peaked at 721 MB.
How much memory and storage does Llama 3.2 3B (GGUF) need?
The catalog budgets 2.5 GB of RAM and 2.1 GB of storage for the Q4_K_M build of Llama 3.2 3B (GGUF). The measured peak footprint on iPhone Air was 721 MB. The 2.5 GB figure is the memory budget the app requires to load the model with its context, while 721 MB is what our benchmark run actually used.
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 Llama 3.2 3B (GGUF)?
Llama 3.2 3B (GGUF) runs on iPhones with 6 GB of RAM or more.
| 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 |
| 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 Llama 3.2 3B (GGUF) do in Pocket AI Lab?
It's a text model for chat, drafting, summaries and quick questions, fully offline once downloaded.
How did Llama 3.2 3B (GGUF) score on the quality suite?
It passed 70 of 118 tasks, a score of 59.3 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 Llama 3.2 3B (GGUF)
| Model | Gen tok/s | pp512 / tg128 | Load s | Peak MB | Score | Date |
|---|---|---|---|---|---|---|
| Llama 3.2 3B (GGUF) | 27.2 ± 0.9 | ~459 / 24.7 | 8.9 | 696 | 78.3 | 2026-09-03 |
| Llama 3.2 3B (GGUF) | 26.9 ± 0.6 | ~459 / 21.9 | 0.2 | 721 | 59.3 | 2026-10-22 |
Other Llama models in the catalog
- Llama 3.2 3B, MLX, 4bit, 23.9 tok/s (throttled)
- Llama 3.1 8B, MLX, 4bit, 7.6 tok/s (throttled)
How do I install Llama 3.2 3B (GGUF)?
Open the Models tab in Pocket AI Lab and tap Llama 3.2 3B (GGUF). The app checks it against your phone's memory, downloads 2.1 GB from Hugging Face and it's ready for offline chat.