How to Run Bonsai 27B on Your Phone (iPhone & Android, Step by Step)
Quick answers:
- You need a phone with 12GB+ RAM for the 1-bit build at a normal 4K context. 16GB Androids can also run the ternary build.
- Total install time is ~15 minutes, most of it the 3.8GB download — use Wi-Fi.
- Expect roughly 8–10 tokens/s (estimated) on 2025–26 flagships — faster than you read.
- Not sure your phone qualifies? Check it first — that's step 1.
Step 1 — Confirm your phone can run it
Bonsai 27B's 1-bit build needs about 6.5GB of usable memory (3.8GB file + KV cache + runtime overhead) — and usable memory is much less than the RAM on the spec sheet. iOS caps a single app at ~65% of total RAM; Android reserves 2–4GB for the system.
The quick rule:
| Your phone | 1-bit (3.8GB) | Ternary (7.2GB) |
|---|---|---|
| 16GB Android (Galaxy S26 Ultra, OnePlus 15…) | ✅ | ✅ |
| 12GB Android / iPhone 17 Pro & Pro Max | ✅ | ❌ |
| 8GB phones (iPhone 16 Pro, Galaxy S24…) | ❌ at 4K context (2K is borderline) | ❌ |
Full per-phone verdicts: Bonsai 27B on the phones we track, or jump straight to your phone, e.g. Galaxy S26 Ultra or iPhone 17 Pro Max.
Step 2 — Pick your build
- 1-bit (Q1_0, 3.8GB) — the one most people should download. Fits 12GB phones with headroom.
- Ternary (Q2_0/PQ2_0, 7.2GB) — slightly higher quality, roughly half the speed (bigger file = more bytes read per token), needs a 16GB Android. Pick it only if you have the RAM and prefer quality over speed.
- On a mid-range phone, consider Ternary Bonsai 8B (2.2GB) instead — same family, far lighter.
Step 3 — Install a local AI app
- iPhone & Android: PocketPal AI — free, open-source, no account. Install from the App Store / Play Store.
- Android alternative: ChatterUI — more sampler controls, same GGUF support.
Step 4 — Download the model
In PocketPal's model hub, search prism-ml/Bonsai-27B-gguf (1-bit) or prism-ml/Ternary-Bonsai-27B-gguf and pick the main model file. On Wi-Fi the 3.8GB download typically takes a few minutes. Skip any small auxiliary files (mtp-*, mmproj-*) — the app only needs the main GGUF unless you enable vision.
Step 5 — Set context to 4K (and Metal on iPhone)
Before the first chat:
- Context length: 4096. These memory numbers assume 4K; every extra 4K of context costs ~1.9GB more KV cache on a 27B model.
- iPhone: enable Metal / GPU acceleration in the app's model settings.
- Close your other apps — on a 12GB iPhone the headroom after loading is ~1.3GB, and iOS will evict the model if memory runs out.
Step 6 — First run: what to expect
Our bandwidth-based estimates (formula, not measured — methodology):
| Phone | Est. speed |
|---|---|
| Galaxy S26 Ultra / OnePlus 15 | ~10 tokens/s |
| iPhone 17 Pro Max / Galaxy S24 Ultra | ~9 tokens/s |
| Pixel 10 Pro / POCO X7 Pro | ~8 tokens/s |
PrismML's own figure for iPhone 17 Pro Max is ~11 tokens/s. Anything above ~8 tokens/s reads faster than you can read; a ~300-word reply lands in under a minute. The first response after loading is slower — that's prompt processing, not generation.
If something goes wrong
- App crashes while loading → not enough free memory. Reboot, load again before opening anything else, or drop context to 2K. If it still dies, your phone needs the 8B build.
- Starts fast, gets slower → thermal throttling; sustained generation heats the chassis within ~10 minutes. Take the case off, pause between long replies.
- Gibberish or repetition → re-download the file (corrupted download) and make sure the app is up to date — Bonsai's quant formats need a recent llama.cpp build.
FAQ
Does it work fully offline? Yes — after the download, inference is on-device. Airplane mode works.
Can it see images? Yes, Bonsai is multimodal — enabling the vision tower adds ~0.5GB of memory.
Is 1-bit quality actually usable? PrismML reports ~90% of full-precision performance across 15 benchmarks. Independent verification is still thin — for coding, compare it against Qwen3.6 27B's smaller siblings on your own prompts. See our Bonsai vs Qwen3.6 comparison.
What about the requirements in detail? Full RAM math per variant and per phone: Can your phone run Bonsai 27B?
Speeds are formula estimates from our fit engine unless marked measured; measured entries land as the community submits them.