Can Gemma 4 E4B run on Nothing Phone (3a)?
YES — Runs, barely
Grade B · 66/100 · formula estimate
What this means
Our estimate says Gemma 4 E4B should fit, but replies are likely to arrive slowly.
Download the Q4_K_M version, which is about 5 GB. We expect it to use about 6.1 GB of the roughly 9 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.
2.3tokens/s
estimated · slower than you read
6.1GB
needed at Q4_K_M
Q4_K_M
quant checked
B
grade · 66/100
needs 6.1 GBusable 9 GB
Snapdragon 7s Gen 312 GB RAMCPU / GPUalso sold with 8 GB
Make it bearable
1
Drop context to 2K — saves ~0.2 GB of KV cache and a little speed.
2
Close every other app before loading — the 2.9 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 2.3 tokens/s — slower than you read. A ~300-word reply takes about 174 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q4_K_M GGUF (5 GB) + mmap overhead | 5.3 |
| KV cache | 4K context window | 0.3 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q4_K_M, 4K context | 6.1 |
| Usable on Nothing Phone (3a) | 12 GB RAM − Android system reserve | 9 |
| Headroom | left for the OS and your other apps | 2.9 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q3_K_M | 4.1 GB | ! Runs, barely | ~2.8 tokens/s |
| IQ4_XS | 4.7 GB | ! Runs, barely | ~2.5 tokens/s |
| Q4_0 | 4.8 GB | ! Runs, barely | ~2.4 tokens/s |
| Q4_K_S | 4.8 GB | ! Runs, barely | ~2.4 tokens/s |
| Q4_K_M BEST HERE | 5 GB | ! Runs, barely | ~2.3 tokens/s |
| Q5_K_M | 5.5 GB | ! Runs, barely | ~2.1 tokens/s |
| Q6_K | 7.1 GB | ! Runs, barely | ~1.6 tokens/s |
| Q8_0 | 8.2 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 E4B Q4_K_M" in the in-app model hub — 5 GB, use Wi-Fi. Search Hugging Face for
unsloth/gemma-4-E4B-it-GGUF and pick the Q4_K_M file.3
Set context to 4K — expect ~2.3 tokens/s on this phone.
Related checks
MORE ON NOTHING PHONE (3A)
GEMMA 4 E4B ON OTHER PHONES