text model · Nemotron · Android
Can I run Nemotron Nano 9B v2 on Generic Android Phone (12GB RAM)?
Yes. Nemotron Nano 9B v2 runs on Generic Android Phone (12GB RAM) at Q4_K_M (~7.6 GB of ~8.5 GB usable).
Fits at Q4_K_M (~7.6 GB of ~8.5 GB usable) but with little headroom. Close background apps, and expect slow generation on a phone.
That figure is at a 4k context and moves about ±15% as context length changes. Generic Android Phone (12GB RAM) leaves ~0.9 GB of headroom.
- Q4_K_M needed
- ~7.6 GB
- Usable on device
- ~8.5 GB
- Device memory
- 12 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
- 9B
- Q4_K_M size
- 6.08 GB
- Q8_0 size
- 8.81 GB
- Context
- 128k
- Memory
- 12 GB ram
- Usable for weights
- ~8.5 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM
You could also run
Run Nemotron Nano 9B v2 on other hardware
FAQ
Can Generic Android Phone (12GB RAM) run Nemotron Nano 9B v2?
Yes. Nemotron Nano 9B v2 runs on Generic Android Phone (12GB RAM) at Q4_K_M (~7.6 GB of ~8.5 GB usable).
How much memory does Nemotron Nano 9B v2 need?
It is a tight fit on Generic Android Phone (12GB RAM). At Q4_K_M the weights are ~6.08 GB; with KV cache and runtime overhead, budget ~7.6 GB at a 4k context.
What is the best tool to run Nemotron Nano 9B v2 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-nano-9b/android-generic-12gb) Sources
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF
- huggingface.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF
- huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2
- huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2/discussions
- layla-network.ai
- ollama.com/library/llama3.1:8b
- ollama.com/library/nemotron-3-nano
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.