Can Ternary Bonsai 8B run on iPhone 15 Pro?
YES — Runs great
Grade S · 85/100 · formula estimate
What this means
Our estimate says Ternary Bonsai 8B should fit comfortably on your iPhone 15 Pro.
Download the PQ2_0 version, which is about 2.2 GB. We expect it to use about 3.5 GB of the roughly 5.2 GB available to a model on this phone.
At the estimated speed, a roughly 300-word answer may take about 38 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
10.5tokens/s
estimated · faster than you read
3.5GB
needed at PQ2_0
PQ2_0
quant checked
S
grade · 85/100
needs 3.5 GBusable 5.2 GB
Apple A17 Pro8 GB RAMMetal
See how fast it feels
Estimated at 10.5 tokens/s — faster than you read. A ~300-word reply takes about 38 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | PQ2_0 GGUF (2.2 GB) + mmap overhead | 2.3 |
| KV cache | 4K context window | 0.6 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at PQ2_0, 4K context | 3.5 |
| Usable on iPhone 15 Pro | 8 GB RAM − iOS reserve (jetsam limit) | 5.2 |
| Headroom | left for the OS and your other apps | 1.7 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| PQ2_0 BEST HERE | 2.2 GB | ✓ Runs great | ~10.5 tokens/s |
| Q2_0 | 2.2 GB | ✓ Runs great | ~10.5 tokens/s |
Get it running in 3 steps
1
Install PocketPal from the App Store — free, no account needed.
2
Download "Ternary Bonsai 8B PQ2_0" in the in-app model hub — 2.2 GB, use Wi-Fi. Search Hugging Face for
prism-ml/Ternary-Bonsai-8B-gguf and pick the PQ2_0 file.3
Set context to 4K and enable Metal — expect ~10.5 tokens/s on this phone.
Related checks
MORE ON IPHONE 15 PRO
TERNARY BONSAI 8B ON OTHER PHONES