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
- iPhone 17 Pro Max Runs well
- iPhone 17 Pro Runs well
- iPhone Air Runs well
- Pixel 10 Pro XL Runs well
- Pixel 10 Pro Runs well
- Pixel 10 Runs well
- Galaxy S26 Ultra Runs well
- Pixel 9 Pro XL Runs well
- Pixel 9 Pro Runs well
- Pixel 9 Runs well
- Pixel 9a Fits
- Pixel 8 Pro Runs well
- Pixel 8 Fits
- Galaxy S25 Ultra Runs well
- Galaxy S25 Runs well
- Galaxy S24 Ultra Runs well
- Galaxy S24 Fits
- Galaxy S23 Ultra Runs well
Tight (close other apps)
- iPhone 17 Tight
- iPhone 16 Pro Max Tight
- iPhone 16 Pro Tight
- iPhone 16 Plus Tight
- iPhone 16 Tight
- iPhone 16e Tight
- iPhone 15 Pro Max Tight
- iPhone 15 Pro Tight