text model · gpt-oss · Android
Can I run gpt-oss 20B on Google Pixel 9 Pro?
No. gpt-oss 20B needs ~13.2 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
Needs ~13.2 GB even at Q4_K_M, but only ~10.5 GB is usable.
- Q4_K_M needed
- ~13.2 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
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
- 21B (MoE, 3.6B active)
- Q4_K_M size
- 11.28 GB
- Context
- 128k
- Ollama tag
- gpt-oss:20b
- Memory
- 16 GB ram
- Usable for weights
- ~10.5 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
What you can run instead
Run gpt-oss 20B on other hardware
FAQ
Can Google Pixel 9 Pro run gpt-oss 20B?
No. gpt-oss 20B needs ~13.2 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
How much memory does gpt-oss 20B need?
Google Pixel 9 Pro does not have enough memory. At Q4_K_M the weights are ~11.28 GB; with KV cache and runtime overhead, budget ~13.2 GB at a 4k context. It is a Mixture-of-Experts model (21B total / 3.6B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run gpt-oss 20B 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.