anziank/grio-qwen2.5-1.5b-instruct-coreml-stateful-int8
Qwen2.5 1.5B (Core ML) on iPhone
How fast does Qwen2.5 1.5B (Core ML) run on iPhone?
On an iPhone Air (A19, iOS 26.6.1), Qwen2.5 1.5B (Core ML) generated 3.0 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 646 tok/s and generated 128 tokens at 2.9 tok/s. Cold load took 39.4 s and the process peaked at 4,354 MB.
How much memory and storage does Qwen2.5 1.5B (Core ML) need?
The catalog budgets 2.5 GB of RAM and 2.3 GB of storage for the int8-W8A16 build of Qwen2.5 1.5B (Core ML). The measured peak footprint on iPhone Air was 4,354 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 Qwen2.5 1.5B (Core ML)?
Qwen2.5 1.5B (Core ML) 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.
Qwen2.5 1.5B (Core ML) is an older model. It stays in the catalog for people who already use it, but the app no longer recommends it.
What can Qwen2.5 1.5B (Core ML) do in Pocket AI Lab?
It's a text model for chat, drafting, summaries and quick questions, fully offline once downloaded.
How did Qwen2.5 1.5B (Core ML) score on the quality suite?
It passed 29 of 118 tasks, a score of 24.6 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 Qwen2.5 1.5B (Core ML)
| Model | Gen tok/s | pp512 / tg128 | Load s | Peak MB | Score | Date |
|---|---|---|---|---|---|---|
| Qwen2.5 1.5B (Core ML) | 3.4 ± 0.2 | ~703 / 3.4 | 40.9 | 4,130 | 26.1 | 2026-09-06 |
| Qwen2.5 1.5B (Core ML) | 3.0 ± 0.3 | ~646 / 2.9 | 39.4 | 4,354 | 24.6 | 2026-10-23 |
Other Qwen models in the catalog
- Qwen 2.5 3B, MLX, 4bit, 26.3 tok/s
- Qwen 2.5 14B, MLX, 4bit
- Qwen2-VL 7B (Vision), MLX, 4bit, 11.6 tok/s (throttled)
- Qwen 3.5 0.8B (GGUF, Vision), llama.cpp, Q4_K_M, 73.7 tok/s
- Qwen 3.5 2B (GGUF, Vision), llama.cpp, Q4_K_M, 36.6 tok/s
- Qwen 3.5 4B (GGUF, Vision), llama.cpp, Q4_K_M, 14.7 tok/s (throttled)
How do I install Qwen2.5 1.5B (Core ML)?
Open the Models tab in Pocket AI Lab and tap Qwen2.5 1.5B (Core ML). The app checks it against your phone's memory, downloads 2.3 GB from Hugging Face and it's ready for offline chat.