Can Gemma 4 31B run on OnePlus 12?
YES — Runs, barely
Grade C · 46/100 · formula estimate
What this means
Our estimate says Gemma 4 31B should fit, but there is very little memory left for the operating system and other apps.
Download the IQ4_XS version, which is about 16.4 GB. We expect it to use about 20 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
20GB
needed at IQ4_XS
IQ4_XS
quant checked
C
grade · 46/100
needs 20 GBusable 20 GB
Snapdragon 8 Gen 324 GB RAMCPU / GPUalso sold with 12/16 GB
Make it bearable
1
Drop context to 2K — saves ~1.1 GB of KV cache and a little speed.
2
Close every other app before loading — the 0 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 | IQ4_XS GGUF (16.4 GB) + mmap overhead | 17.2 |
| KV cache | 4K context window | 2.2 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at IQ4_XS, 4K context | 20 |
| Usable on OnePlus 12 | 24 GB RAM − Android system reserve | 20 |
| Headroom | left for the OS and your other apps | 0 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q3_K_M | 14.7 GB | ! Runs, barely | ~2.4 tokens/s |
| IQ4_XS BEST HERE | 16.4 GB | ! Runs, barely | ~2.1 tokens/s |
| Q4_0 | 17.3 GB | ✕ Won't fit | won't fit |
| Q4_K_S | 17.4 GB | ✕ Won't fit | won't fit |
| Q4_K_M | 18.3 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 21.7 GB | ✕ Won't fit | won't fit |
| Q6_K | 25.2 GB | ✕ Won't fit | won't fit |
| Q8_0 | 32.6 GB | ✕ Won't fit | won't fit |
Get it running in 3 steps
1
Install PocketPal from the Play Store — free, no account needed.
2
Download "Gemma 4 31B IQ4_XS" in the in-app model hub — 16.4 GB, use Wi-Fi. Search Hugging Face for
unsloth/gemma-4-31B-it-GGUF and pick the IQ4_XS file.3
Set context to 4K — expect ~2.1 tokens/s on this phone.
Related checks
MORE ON ONEPLUS 12
GEMMA 4 31B ON OTHER PHONES