text model · Gemma · Android
Can I run Gemma 4 12B on Samsung Galaxy S26 Ultra (16GB, 1TB config)?
Yes. Gemma 4 12B runs on Samsung Galaxy S26 Ultra (16GB, 1TB config) at Q4_K_M (~8.7 GB of ~12 GB usable).
Runs at Q4_K_M using ~8.7 GB of ~12 GB usable.
That figure is at a 4k context and moves about ±15% as context length changes. Samsung Galaxy S26 Ultra (16GB, 1TB config) leaves ~3.3 GB of headroom.
- Q4_K_M needed
- ~8.7 GB
- Usable on device
- ~12 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 12B
- Q4_K_M size
- 7.12 GB
- Q8_0 size
- 12.67 GB
- Context
- 256k
- Ollama tag
- gemma4:12b
- 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 Gemma 4 12B on other hardware
FAQ
Can Samsung Galaxy S26 Ultra (16GB, 1TB config) run Gemma 4 12B?
Yes. Gemma 4 12B runs on Samsung Galaxy S26 Ultra (16GB, 1TB config) at Q4_K_M (~8.7 GB of ~12 GB usable).
How much memory does Gemma 4 12B need?
Samsung Galaxy S26 Ultra (16GB, 1TB config) has room to spare. At Q4_K_M the weights are ~7.12 GB; with KV cache and runtime overhead, budget ~8.7 GB at a 4k context.
What is the best tool to run Gemma 4 12B 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.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/gemma-4-12b/samsung-s26-ultra) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.