How fast does Gemma 2 2B run on iPhone?
On an iPhone Air (A19, iOS 26.6.1), Gemma 2 2B generated 30.3 tokens per second in Pocket AI Lab 1.1.0, averaged over 3 runs of 200 tokens (± 0.3).
On the standard llama-bench style probe it read a 512-token prompt at about 277 tok/s and generated 128 tokens at 27.4 tok/s. Cold load took 3.7 s and the process peaked at 2,148 MB.
How much memory and storage does Gemma 2 2B need?
The catalog budgets 1.6 GB of RAM and 1.5 GB of storage for the 4bit build of Gemma 2 2B. The measured peak footprint on iPhone Air was 2,148 MB.
Its backend copies weights into the app's memory, so the app checks it against the per-app limit iOS enforces. On a 6 GB iPhone that limit is much lower than 6 GB.
Which iPhones can run Gemma 2 2B?
Gemma 2 2B 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) | Not measured yet |
| 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 Gemma 2 2B do in Pocket AI Lab?
It's a text model for chat, drafting, summaries and quick questions, fully offline once downloaded.
How did Gemma 2 2B score on the quality suite?
It passed 48 of 118 tasks, a score of 40.7 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 Gemma 2 2B
| Model | Gen tok/s | pp512 / tg128 | Load s | Peak MB | Score | Date |
|---|---|---|---|---|---|---|
| Gemma 2 2B | 29.7 ± 1.4 | ~272 / 24.7 | 3.7 | 2,130 | 56.5 | 2026-09-03 |
| Gemma 2 2B | 37.9 ± 0.5 | ~269 / 35.8 | 2.0 | 2,089 | 56.5 | 2026-09-04 |
| Gemma 2 2B | 30.3 ± 0.3 | ~277 / 27.4 | 3.7 | 2,148 | 40.7 | 2026-10-22 |
Other Gemma models in the catalog
- Gemma 3 4B (Vision), MLX, 4bit, 21.8 tok/s (throttled)
- Gemma 3 12B (Vision), MLX, 4bit
- Gemma 3 4B (GGUF, Vision), llama.cpp, Q4_K_M, 20.7 tok/s (throttled)
- Gemma 4 E2B (GGUF, Vision), llama.cpp, Q4_K_M, 35.0 tok/s
How do I install Gemma 2 2B?
Open the Models tab in Pocket AI Lab and tap Gemma 2 2B. The app checks it against your phone's memory, downloads 1.5 GB from Hugging Face and it's ready for offline chat.