Nemotron · 9B · Desktop / import

Nemotron Nano 9B v2 on a phone

NVIDIA 9B local model — stronger than 8B class if you have the RAM.

Parameters
9B
Typical Q4
~5.2 GB (Q4)
RAM to budget
~8 GB
Engines
GGUF

Get it running

nvidia/NVIDIA-Nemotron-Nano-9B-v2. Prefer Q4 GGUF on Mac/GPU. Hugging Face: nvidia/NVIDIA-Nemotron-Nano-9B-v2.

Load in LM Studio or Ollama, then chat from the phone.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

Tight (close other apps)

  • None in this guide — use a Mac or Connect.