Can Ternary Bonsai 1.7B run on Galaxy S25 Ultra?
YES — Runs great
Grade S · 100/100 · formula estimate
What this means
Our estimate says Ternary Bonsai 1.7B should fit comfortably on your Galaxy S25 Ultra.
Download the PQ2_0 version, which is about 0.5 GB. We expect it to use about 1.2 GB of the roughly 12 GB available to a model on this phone.
At the estimated speed, a roughly 300-word answer may take about 6 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
69.1tokens/s
estimated · instant
1.2GB
needed at PQ2_0
PQ2_0
quant checked
S
grade · 100/100
needs 1.2 GBusable 12 GB
Snapdragon 8 Elite16 GB RAMCPU / GPUalso sold with 12 GB
See how fast it feels
Estimated at 69.1 tokens/s — instant. A ~300-word reply takes about 6 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 Galaxy S25 Ultra | 16 GB RAM − Android system reserve | 12 |
| Headroom | left for the OS and your other apps | 10.8 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| PQ2_0 BEST HERE | 0.5 GB | ✓ Runs great | ~69.1 tokens/s |
| Q2_0 | 0.5 GB | ✓ Runs great | ~69.1 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 ~69.1 tokens/s on this phone.
Related checks
MORE ON GALAXY S25 ULTRA
TERNARY BONSAI 1.7B ON OTHER PHONES