Can UI-Mate 9B run on iPhone 17 Pro?
YES — Runs, barely
Formula estimate
What this means
The checked Q4_K_M version should run, but there is very little memory left for the operating system and other apps. The smaller Q2_K version is the safer choice.
Download the Q2_K version, which is about 4.1 GB. We expect it to use about 5.5 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 48 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
5.9tokens/s
estimated · reading pace
7.4GB
needed at Q4_K_M
Q4_K_M
quant checked
needs 7.4 GBusable 7.8 GB
Apple A19 Pro12 GB RAMMetal
Make it bearable
1
Drop to Q2_K (4.1 GB) — it runs comfortably here at ~8.4 tokens/s. Recommended over Q4_K_M.
2
Drop context to 2K — saves ~0.3 GB of KV cache and a little speed.
3
Close every other app before loading — the 0.4 GB headroom is real; iOS may evict the model otherwise.
4
Expect throttling after ~10 min of sustained generation on a phone chassis.
See how fast it feels
Estimated at 5.9 tokens/s — reading pace. A ~300-word reply takes about 68 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_M GGUF (5.9 GB) + mmap overhead | 6.2 |
| KV cache | 4K context window | 0.6 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_M, 4K context | 7.4 |
| Working budget | 12 GB RAM − iOS reserve (jetsam limit) | 7.8 |
| Headroom | remaining inside the working budget | 0.4 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K BEST HERE | 4.1 GB | ✓ Runs great | ~8.4 tokens/s |
| Q3_K_M | 4.9 GB | ! Runs, barely | ~7.1 tokens/s |
| IQ4_XS | 5.2 GB | ! Runs, barely | ~6.6 tokens/s |
| Q4_0 | 5.5 GB | ! Runs, barely | ~6.3 tokens/s |
| Q4_K_S | 5.6 GB | ! Runs, barely | ~6.2 tokens/s |
| Q4_K_M | 5.9 GB | ! Runs, barely | ~5.9 tokens/s |
| Q5_K_M | 6.9 GB | ✕ Won't fit | won't fit |
| Q6_K | 7.7 GB | ✕ Won't fit | won't fit |
| Q8_0 | 9.5 GB | ✕ Won't fit | won't fit |
Get your first offline chat working
Recommended app: PocketPal. Follow the point-and-click steps below. The speed above is an estimate, not a measurement from this exact app and phone.
1
Install or update PocketPal from the App Store. It is free and does not require an account. Use a current version so its loader supports newer model architectures.
2
Open the exact model. In PocketPal, go to Models → + → Add from Hugging Face, then paste
bartowski/tencent_UI-Mate-9B-GGUF.3
Choose the Q2_K GGUF file. The download is about 4.1 GB, so use Wi-Fi and keep the app open. Choose the main GGUF weights, not a vision projector, mmproj, or other helper file.
4
Tap Download, then Load. Start with a 4K (4096-token) context. Keep PocketPal’s default Metal acceleration; this does not require Xcode.
5
Send a simple first prompt. Try “Explain why the sky is blue in three sentences.” This page estimates about 8.4 tokens/s, but that number is not a PocketPal measurement unless it carries a ✓ Verified label.
6
Confirm it is really offline. After the first reply, turn on airplane mode and ask a second question. If it still answers, the model is running on your phone.
If it does not work
- Model not listed: update PocketPal and paste the exact repository
bartowski/tencent_UI-Mate-9B-GGUF. - App closes while loading: close other apps, restart the phone, and try 2K context. If it still closes, choose a smaller model.
- No offline reply: confirm that the Q2_K GGUF file is loaded in the chat rather than a remote model.
Related checks
More on iPhone 17 Pro
UI-Mate 9B on other phones