Can DeepSeek R1 Distill 7B run on AQUOS sense10?
YES — Runs, barely
Grade C · 48/100 · formula estimate
What this means
Our estimate says DeepSeek R1 Distill 7B 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 4.5 GB. We expect it to use about 5.9 GB of the roughly 6 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.
2.6tokens/s
estimated · slower than you read
5.9GB
needed at Q4_K_S
Q4_K_S
quant checked
C
grade · 48/100
needs 5.9 GBusable 6 GB
Snapdragon 7s Gen 38 GB RAMCPU / GPUalso sold with 6 GB
Make it bearable
1
Drop context to 2K — saves ~0.3 GB of KV cache and a little speed.
2
Close every other app before loading — the 0.1 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 2.6 tokens/s — slower than you read. A ~300-word reply takes about 154 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_S GGUF (4.5 GB) + mmap overhead | 4.7 |
| KV cache | 4K context window | 0.5 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_S, 4K context | 5.9 |
| Usable on AQUOS sense10 | 8 GB RAM − Android system reserve | 6 |
| Headroom | left for the OS and your other apps | 0.1 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_K | 3 GB | ! Runs, barely | ~3.8 tokens/s |
| Q3_K_M | 3.8 GB | ! Runs, barely | ~3 tokens/s |
| IQ4_XS | 4.2 GB | ! Runs, barely | ~2.7 tokens/s |
| Q4_0 | 4.4 GB | ! Runs, barely | ~2.6 tokens/s |
| Q4_K_S BEST HERE | 4.5 GB | ! Runs, barely | ~2.6 tokens/s |
| Q4_K_M | 4.7 GB | ✕ Won't fit | won't fit |
| Q5_K_M | 5.4 GB | ✕ Won't fit | won't fit |
| Q6_K | 6.3 GB | ✕ Won't fit | won't fit |
| Q8_0 | 8.1 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 "DeepSeek R1 Distill 7B Q4_K_S" in the in-app model hub — 4.5 GB, use Wi-Fi. Search Hugging Face for
bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF and pick the Q4_K_S file.3
Set context to 4K — expect ~2.6 tokens/s on this phone.
Related checks
MORE ON AQUOS SENSE10
DEEPSEEK R1 DISTILL 7B ON OTHER PHONES