---
title: Nemotron 3 Nano 4B llama.cpp
emoji: 🤖
colorFrom: green
colorTo: gray
sdk: docker
app_port: 7860
pinned: false
license: other
---

# Nemotron 3 Nano 4B llama.cpp Server

Docker Space serving the base GGUF model `mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF` with `llama.cpp`.

Default file: `NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf`.

No LoRA or merged ASCII-art adapter is used.

The server exposes the llama.cpp OpenAI-compatible API on port 7860.