Can Qwen3 1.7B run on iPhone 17 Pro?
YES — Runs great
Grade S · 100/100 · formula estimate
What this means
Our estimate says Qwen3 1.7B should fit comfortably on your iPhone 17 Pro.
Download the Q8_0 version, which is about 1.8 GB. We expect it to use about 2.6 GB of the roughly 7.8 GB available to a model on this phone.
At the estimated speed, a roughly 300-word answer may take about 21 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
19.2tokens/s
estimated · instant
2.6GB
needed at Q8_0
Q8_0
quant checked
S
grade · 100/100
needs 2.6 GBusable 7.8 GB
Apple A19 Pro12 GB RAMMetal
See how fast it feels
Estimated at 19.2 tokens/s — instant. A ~300-word reply takes about 21 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q8_0 GGUF (1.8 GB) + mmap overhead | 1.9 |
| KV cache | 4K context window | 0.1 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q8_0, 4K context | 2.6 |
| Usable on iPhone 17 Pro | 12 GB RAM − iOS reserve (jetsam limit) | 7.8 |
| Headroom | left for the OS and your other apps | 5.2 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q8_0 BEST HERE | 1.8 GB | ✓ Runs great | ~19.2 tokens/s |
Get it running in 3 steps
1
Install PocketPal from the App Store — free, no account needed.
2
Download "Qwen3 1.7B Q8_0" in the in-app model hub — 1.8 GB, use Wi-Fi. Search Hugging Face for
Qwen/Qwen3-1.7B-GGUF and pick the Q8_0 file.3
Set context to 4K and enable Metal — expect ~19.2 tokens/s on this phone.
Related checks
MORE ON IPHONE 17 PRO
QWEN3 1.7B ON OTHER PHONES