Can UI-Mate 27B run on ROG Phone 9 Pro?
YES — Runs, barely
Formula estimate
What this means
Our estimate says UI-Mate 27B should fit, but there is very little memory left for the operating system and other apps.
Download the Q4_K_S version, which is about 16.5 GB. We expect it to use about 19.8 GB of the roughly 20 GB available to a model on this phone.
At the estimated speed, a roughly 300-word answer may take about 3 minutes to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
2.1tokens/s
estimated · slower than you read
19.8GB
needed at Q4_K_S
Q4_K_S
quant checked
needs 19.8 GBusable 20 GB
Snapdragon 8 Elite24 GB RAMCPU / GPUAlso sold with 16 GB
Make it bearable
1
Drop context to 2K — saves ~1 GB of KV cache and a little speed.
2
Close every other app before loading — the 0.2 GB headroom is real; Android may kill the app otherwise.
3
Expect throttling after ~10 min of sustained generation on a phone chassis.
See how fast it feels
Estimated at 2.1 tokens/s — slower than you read. A ~300-word reply takes about 190 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_S GGUF (16.5 GB) + mmap overhead | 17.3 |
| KV cache | 4K context window | 1.9 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_S, 4K context | 19.8 |
| Working budget | 24 GB RAM − Android system reserve | 20 |
| Headroom | remaining inside the working budget | 0.2 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K | 11.6 GB | ! Runs, barely | ~3 tokens/s |
| Q3_K_M | 14.4 GB | ! Runs, barely | ~2.4 tokens/s |
| IQ4_XS | 15.3 GB | ! Runs, barely | ~2.3 tokens/s |
| Q4_0 | 16.1 GB | ! Runs, barely | ~2.1 tokens/s |
| Q4_K_S BEST HERE | 16.5 GB | ! Runs, barely | ~2.1 tokens/s |
| Q4_K_M | 17.5 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 20.5 GB | ✕ Won't fit | won't fit |
| Q6_K | 23.2 GB | ✕ Won't fit | won't fit |
| Q8_0 | 28.7 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 Google Play. 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-27B-GGUF.3
Choose the Q4_K_S GGUF file. The download is about 16.5 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 the app’s default Android backend for the first run.
5
Send a simple first prompt. Try “Explain why the sky is blue in three sentences.” This page estimates about 2.1 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-27B-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 Q4_K_S GGUF file is loaded in the chat rather than a remote model.
Related checks
More on ROG Phone 9 Pro
UI-Mate 27B on other phones