Can Bonsai 27B (1-bit) run on Galaxy A37 5G?
YES — Runs, barely
Formula estimate
What this means
Our estimate says Bonsai 27B (1-bit) should fit, but replies are likely to arrive slowly.
Download the Q1_0 version, which is about 3.8 GB. We expect it to use about 4.8 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 2 minutes to finish.
This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.
3tokens/s
estimated · reading pace
4.8GB
needed at Q1_0
Q1_0
quant checked
needs 4.8 GBusable 9 GB
Exynos 148012 GB RAMCPU / GPUAlso sold with 6/8 GB
Make it bearable
1
Drop context to 2K — saves ~0.2 GB of KV cache and a little speed.
2
Close every other app before loading — the 4.2 GB headroom is real; Android may kill the app otherwise.
3
Expect throttling after ~10 min of sustained generation on a phone chassis.
See how fast it feels
Estimated at 3 tokens/s — reading pace. A ~300-word reply takes about 133 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 | 0.3 |
| Runtime | llama.cpp + app overhead | 0.6 |
| Total needed | at Q1_0, 4K context | 4.8 |
| Working budget | 12 GB RAM − Android system reserve | 9 |
| Headroom | remaining inside the working budget | 4.2 |
Pick your quant
| Quant | Download | Verdict | Speed |
|---|---|---|---|
| Q1_0 BEST HERE | 3.8 GB | ! Runs, barely | ~3 tokens/s |
Get your first offline chat working
1
Install or update PocketPal from Google Play. It is free and does not require an account. Use a current version so its loader supports newer model architectures.
2
Open the exact model. Tap Open in PocketPal. If that does not open the app, go to Models → + → Add from Hugging Face and paste
prism-ml/Bonsai-27B-gguf.3
Choose Bonsai-27B-Q1_0.gguf. The download is about 3.8 GB, so use Wi-Fi and keep the app open. Do not choose F16, mmproj, mtp, or dspark helper files.
4
Tap Download, then Load. Start with a 4K (4096-token) context. Keep the app’s default Android backend for the first run.
5
Send a simple first prompt. Try “Explain why the sky is blue in three sentences.” This page estimates about 3 tokens/s, but that number is not a PocketPal measurement unless it carries a ✓ Verified label.
6
Confirm it is really offline. After the first reply, turn on airplane mode and ask a second question. If it still answers, the model is running on your phone.
If it does not work
- Model not listed: update PocketPal and paste the exact repository
prism-ml/Bonsai-27B-gguf. - App closes while loading: close other apps, restart the phone, and try 2K context. If it still closes, choose a smaller model.
- No offline reply: confirm that Bonsai-27B-Q1_0.gguf is loaded in the chat rather than a remote model.
Related checks
More on Galaxy A37 5G
Bonsai 27B (1-bit) on other phones