Can OneJev 27B run on Huawei Mate X7?
Estimated weights fit · custom workflow required
Weight fit is not phone app support
The tracked Q2_K weights are 10.7GB; the generic working-memory estimate is 13.7GB against 16GB usable. Image inputs need additional projector memory.
OneJev scores typed decisions in a single forward pass, not chat replies. The decode estimates below are not measured decision latency. The publisher's qev server and System One client are required; AICanRun has not verified a phone app route.
Not measured
decision latency
13.7GB
needed at Q2_K
Q2_K
quant checked
needs 13.7 GBusable 16 GB
Kirin 9030 Pro20 GB RAMCPU / GPUAlso sold with 12/16 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 2.3 GB headroom is real; Android may kill the app otherwise.
3
Expect throttling after ~10 min of sustained generation on a phone chassis.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q2_K GGUF (10.7 GB) + mmap overhead | 11.2 |
| KV cache | 4K context window | 1.9 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q2_K, 4K context | 13.7 |
| Working budget | 20 GB RAM − Android system reserve | 16 |
| Headroom | remaining inside the working budget | 2.3 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K BEST HERE | 10.7 GB | ! Runs, barely | ~3.2 tokens/s |
| Q3_K_M | 13.3 GB | ✕ Won't fit | won't fit |
| IQ4_XS | 15.2 GB | ✕ Won't fit | won't fit |
| Q4_K_S | 15.6 GB | ✕ Won't fit | won't fit |
| Q4_K_M | 16.5 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 19.2 GB | ✕ Won't fit | won't fit |
| Q6_K | 22.1 GB | ✕ Won't fit | won't fit |
| Q8_0 | 28.6 GB | ✕ Won't fit | won't fit |
Use the right workflow for this model
The model fits in memory, but it is not an ordinary chat model.
This model is designed to return calibrated probabilities for typed choices from text or images. PocketPal does not provide the required the publisher's qev server and System One client; image inputs also need a vision projector, 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 Llama 3.2 3BRelated checks
More on Huawei Mate X7
OneJev 27B on other phones