Can Ternary Bonsai 1.7B run on Nothing Phone (3a)?
YES — Runs great
Grade S · 100/100 · formula estimate
What this means
Our estimate says Ternary Bonsai 1.7B should fit comfortably on your Nothing Phone (3a).
Download the PQ2_0 version, which is about 0.5 GB. We expect it to use about 1.2 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 17 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
23tokens/s
estimated · instant
1.2GB
needed at PQ2_0
PQ2_0
quant checked
S
grade · 100/100
needs 1.2 GBusable 9 GB
Snapdragon 7s Gen 312 GB RAMCPU / GPUalso sold with 8 GB
See how fast it feels
Estimated at 23 tokens/s — instant. A ~300-word reply takes about 17 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | PQ2_0 GGUF (0.5 GB) + mmap overhead | 0.5 |
| KV cache | 4K context window | 0.1 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at PQ2_0, 4K context | 1.2 |
| Usable on Nothing Phone (3a) | 12 GB RAM − Android system reserve | 9 |
| Headroom | left for the OS and your other apps | 7.8 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| PQ2_0 BEST HERE | 0.5 GB | ✓ Runs great | ~23 tokens/s |
| Q2_0 | 0.5 GB | ✓ Runs great | ~23 tokens/s |
Get it running in 3 steps
1
Install PocketPal from the Play Store — free, no account needed.
2
Download "Ternary Bonsai 1.7B PQ2_0" in the in-app model hub — 0.5 GB, use Wi-Fi. Search Hugging Face for
prism-ml/Ternary-Bonsai-1.7B-gguf and pick the PQ2_0 file.3
Set context to 4K — expect ~23 tokens/s on this phone.
Related checks
MORE ON NOTHING PHONE (3A)
TERNARY BONSAI 1.7B ON OTHER PHONES