Can AREX-2 27B run on Huawei Mate X7?
What this means
Our estimate says AREX-2 27B should fit, but replies are likely to arrive slowly.
Download the Q2_K version, which is about 10.6 GB. We expect it to use about 13.6 GB of the roughly 16 GB available to a model on this phone.
At the estimated speed, a roughly 300-word answer may take about 2 minutes to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
Make it bearable
See how fast it feels
Estimated at 3.3 tokens/s — reading pace. A ~300-word reply takes about 121 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q2_K GGUF (10.6 GB) + mmap overhead | 11.1 |
| KV cache | 4K context window | 1.9 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q2_K, 4K context | 13.6 |
| Working budget | 20 GB RAM − Android system reserve | 16 |
| Headroom | remaining inside the working budget | 2.4 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K BEST HERE | 10.6 GB | ! Runs, barely | ~3.3 tokens/s |
| Q3_K_M | 13.2 GB | ✕ Won't fit | won't fit |
| IQ4_XS | 15.2 GB | ✕ Won't fit | won't fit |
| Q4_0 | 16.1 GB | ✕ Won't fit | won't fit |
| Q4_K_S | 16.1 GB | ✕ Won't fit | won't fit |
| Q4_K_M | 17.2 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 20.7 GB | ✕ Won't fit | won't fit |
| Q6_K | 23.6 GB | ✕ Won't fit | won't fit |
| Q8_0 | 28.7 GB | ✕ Won't fit | won't fit |
Use the right workflow for this model
This model is designed to iterate on coding and deep-research tasks using tool results and feedback. PocketPal does not provide the required a research or coding harness that executes tools and returns feedback between rounds, so the tracked file is not a beginner phone-chat path.
Read the publisher workflow ↗If you only want a normal private chat, use this simpler model instead:
Check Qwen 3.6 27B