How fast does Gemma 4 E2B (GGUF, Vision) run on iPhone?
On an iPhone Air (A19, iOS 26.6.1), Gemma 4 E2B (GGUF, Vision) generated 35.0 tokens per second in Pocket AI Lab 1.1.0, averaged over 3 runs of 200 tokens (± 2.3).
On the standard llama-bench style probe it read a 512-token prompt at about 708 tok/s and generated 128 tokens at 32.8 tok/s. Cold load took 2.6 s and the process peaked at 1,490 MB.
How much memory and storage does Gemma 4 E2B (GGUF, Vision) need?
The catalog budgets 5.0 GB of RAM and 4.1 GB of storage for the Q4_K_M build of Gemma 4 E2B (GGUF, Vision). The measured peak footprint on iPhone Air was 1,490 MB. The 5.0 GB figure is the memory budget the app requires to load the model with its context, while 1,490 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 Gemma 4 E2B (GGUF, Vision)?
Gemma 4 E2B (GGUF, Vision) runs on iPhones with 8 GB of RAM or more. On 8 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 | ✗ Too big |
| 8 GB | iPhone 15 Pro, 16, 16 Plus, 16 Pro, 16e, 17, 17e | ≈ Runs, little headroom |
| 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 4 E2B (GGUF, Vision) do in Pocket AI Lab?
It's a vision-language model, so besides text chat it can describe photos you attach to a message.
How did Gemma 4 E2B (GGUF, Vision) score on the quality suite?
It passed 75 of 118 tasks, a score of 63.6 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 4 E2B (GGUF, Vision)
| Model | Gen tok/s | pp512 / tg128 | Load s | Peak MB | Score | Date |
|---|---|---|---|---|---|---|
| Gemma 4 E2B (GGUF, Vision) | 34.9 ± 1.2 | ~740 / 32.2 | 2.9 | 1,420 | 63.6 | 2026-10-21 |
| Gemma 4 E2B (GGUF, Vision) | 35.0 ± 2.3 | ~708 / 32.8 | 2.6 | 1,490 | 63.6 | 2026-10-23 |
Other Gemma models in the catalog
- Gemma 2 2B, MLX, 4bit, 30.3 tok/s
- 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)
The other Gemma 4 sizes (E4B, 12B, 26B A4B and 31B) and the iPhones that can run each one are covered in Gemma 4 on iPhone.
How do I install Gemma 4 E2B (GGUF, Vision)?
Open the Models tab in Pocket AI Lab and tap Gemma 4 E2B (GGUF, Vision). The app checks it against your phone's memory, downloads 4.1 GB from Hugging Face and it's ready for offline chat.