text model · Nemotron 3 · Android
Can I run Nemotron 3 Ultra 550B-A55B on Google Pixel 10 Pro?
No. Nemotron 3 Ultra 550B-A55B needs ~341 GB even at Q4_K_M, but Google Pixel 10 Pro only has ~10.5 GB usable.
Needs ~341 GB even at Q4_K_M, but only ~10.5 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 330.5 GB: Nemotron 3 Ultra 550B-A55B needs roughly 341 GB at Q4_K_M and Google Pixel 10 Pro leaves only about 10.5 GB usable for a model. No single tracked device has enough memory; Nemotron 3 Ultra 550B-A55B needs a multi-GPU or high-memory rig.
- Q4_K_M needed
- ~341 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 550B (MoE, 55B active)
- Q4_K_M size
- 334.55 GB
- Q8_0 size
- 544.13 GB
- Context
- 256k
- 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)
What you can run instead
FAQ
Can Google Pixel 10 Pro run Nemotron 3 Ultra 550B-A55B?
No. Nemotron 3 Ultra 550B-A55B needs ~341 GB even at Q4_K_M, but Google Pixel 10 Pro only has ~10.5 GB usable.
How much memory does Nemotron 3 Ultra 550B-A55B need?
Google Pixel 10 Pro does not have enough memory. At Q4_K_M the weights are ~334.55 GB; with KV cache and runtime overhead, budget ~341 GB at a 4k context. It is a Mixture-of-Experts model (550B total / 55B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Nemotron 3 Ultra 550B-A55B 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/nemotron-3-ultra-550b-a55b/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
- gsmarena.com
- huggingface.co/nvidia
- huggingface.co/unsloth
- layla-network.ai
- ollama.com
- 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.