text model · Gemma · Android
Can I run Gemma 3 4B on Google Pixel 10 Pro?
Yes. Gemma 3 4B runs on Google Pixel 10 Pro at Q4_K_M (~3.8 GB of ~10.5 GB usable).
Runs at Q4_K_M using ~3.8 GB of ~10.5 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Google Pixel 10 Pro leaves ~6.7 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~3.8 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~7 W
- Electricity / 1M tokens
- ~$0.02
- Pays for itself after
- ~2,081M tok
At ~$0.15/kWh and the estimated ~14 tok/s, a million generated tokens costs about $0.02 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$999 Google Pixel 10 Pro pays for itself after roughly 2,081 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 4B
- Q4_K_M size
- 2.49 GB
- Q8_0 size
- 4.13 GB
- Context
- 128k
- Ollama tag
- gemma3:4b
- Memory
- 16 GB ram
- Usable for weights
- ~10.5 GB
- Power draw
- ~7 W
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
You could also run
Run Gemma 3 4B on other hardware
FAQ
Can Google Pixel 10 Pro run Gemma 3 4B?
Yes. Gemma 3 4B runs on Google Pixel 10 Pro at Q4_K_M (~3.8 GB of ~10.5 GB usable).
How much memory does Gemma 3 4B need?
Google Pixel 10 Pro has room to spare. At Q4_K_M the weights are ~2.49 GB; with KV cache and runtime overhead, budget ~3.8 GB at a 4k context.
What is the best tool to run Gemma 3 4B 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-3-4b/pixel-10-pro) Sources
- 9to5google.com
- gadgetversus.com
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- gorilla.cs.berkeley.edu
- gsmarena.com
- huggingface.co
- layla-network.ai
- lmarena.ai
- ollama.com/library/gemma3
- ollama.com/library/gemma3/tags
- store.google.com/product/pixel_10_pro
- store.google.com/product/pixel_10_pro_specs
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.