Can Bonsai 27B (1-bit) run on Galaxy S23 Ultra?
YES — Runs great
Grade A · 81/100 · formula estimate
What this means
Our estimate says Bonsai 27B (1-bit) should fit comfortably on your Galaxy S23 Ultra.
Download the Q1_0 version, which is about 3.8 GB. We expect it to use about 6.5 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 50 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
8tokens/s
estimated · faster than you read
6.5GB
needed at Q1_0
Q1_0
quant checked
A
grade · 81/100
needs 6.5 GBusable 9 GB
Snapdragon 8 Gen 212 GB RAMCPU / GPUalso sold with 8 GB
See how fast it feels
Estimated at 8 tokens/s — faster than you read. A ~300-word reply takes about 50 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q1_0 GGUF (3.8 GB) + mmap overhead | 4 |
| KV cache | 4K context window | 1.9 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q1_0, 4K context | 6.5 |
| Usable on Galaxy S23 Ultra | 12 GB RAM − Android system reserve | 9 |
| Headroom | left for the OS and your other apps | 2.5 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q1_0 BEST HERE | 3.8 GB | ✓ Runs great | ~8 tokens/s |
Get it running in 3 steps
1
Install PocketPal from the Play Store — free, no account needed.
2
Download "Bonsai 27B (1-bit) Q1_0" in the in-app model hub — 3.8 GB, use Wi-Fi. Search Hugging Face for
prism-ml/Bonsai-27B-gguf and pick the Q1_0 file.3
Set context to 4K — expect ~8 tokens/s on this phone.
Related checks
MORE ON GALAXY S23 ULTRA
BONSAI 27B (1-BIT) ON OTHER PHONES