Nemotron · 4B · Desktop / import

Nemotron 3 Nano 4B on a phone

NVIDIA’s 2026 tiny Nemotron — dense 4B-class, aimed at local agents.

Parameters
4B
Typical Q4
~2.5 GB (Q4)
RAM to budget
~3.8 GB
Engines
GGUF

Get it running

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16. Use a GGUF quant on phone; BF16 is a desktop download. Hugging Face: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16.

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)