Can Ternary Bonsai 4B run on Xiaomi 18 Fold?
YES — Runs great
Formula estimate
What this means
Our estimate says Ternary Bonsai 4B should fit comfortably on your Xiaomi 18 Fold.
Download the Q2_0 version, which is about 1.1 GB. We expect it to use about 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 9 seconds to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
46.6tokens/s
estimated · instant
2GB
needed at Q2_0
Q2_0
quant checked
needs 2 GBusable 12 GB
Xiaomi XRING O316 GB RAMCPU / GPUAlso sold with 12 GB
See how fast it feels
Estimated at 46.6 tokens/s — instant. A ~300-word reply takes about 9 seconds on this phone.
Where the memory goes
| Component | Detail | GB |
|---|---|---|
| Model weights | Q2_0 GGUF (1.1 GB) + mmap overhead | 1.2 |
| KV cache | 4K context window | 0.3 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q2_0, 4K context | 2 |
| Working budget | 16 GB RAM − Android system reserve | 12 |
| Headroom | remaining inside the working budget | 10 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q2_0 BEST HERE | 1.1 GB | ✓ Runs great | ~46.6 tokens/s |
| Q2_0_g64 | 1.1 GB | ✓ Runs great | ~46.6 tokens/s |
Use the supported phone path
The model fits in memory, but this exact download is not a PocketPal model.
The current App Store and Play Store versions of PocketPal cannot load this tracked ternary file. Memory fit does not make this exact download beginner-ready.
For the same kind of chat in PocketPal, use this supported build instead:
Check Bonsai 27B (1-bit)Related checks
More on Xiaomi 18 Fold
Ternary Bonsai 4B on other phones