text model · phi · Android
Can I run Phi-4 14B on Samsung Galaxy S25 Ultra (16GB, 1TB config only)?
Yes. Phi-4 14B runs on Samsung Galaxy S25 Ultra (16GB, 1TB config only) at Q4_K_M (~10.8 GB of ~12 GB usable).
Fits at Q4_K_M (~10.8 GB of ~12 GB usable) but with little headroom, close other apps.
- Q4_K_M needed
- ~10.8 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.). NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.
- Parameters
- 14B
- Q4_K_M size
- 9.05 GB
- Q8_0 size
- 15.58 GB
- Context
- 16k
- Ollama tag
- phi4:14b
- Memory
- 16 GB ram
- Usable for weights
- ~12 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
You could also run
Run Phi-4 14B on other hardware
FAQ
Can Samsung Galaxy S25 Ultra (16GB, 1TB config only) run Phi-4 14B?
Yes. Phi-4 14B runs on Samsung Galaxy S25 Ultra (16GB, 1TB config only) at Q4_K_M (~10.8 GB of ~12 GB usable).
How much memory does Phi-4 14B need?
It is a tight fit on Samsung Galaxy S25 Ultra (16GB, 1TB config only). At Q4_K_M the weights are ~9.05 GB; with KV cache and runtime overhead, budget ~10.8 GB at a 4k context.
What is the best tool to run Phi-4 14B on Android?
On Android, PocketPal AI (Polished app, download GGUF and run offline.) is the go-to option. NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.
Sources
Memory figures are estimates. See methodology.