1bit-MONSTER/NVIDIA-Nemotron-3-Nano-4B-GGUF overview
NVIDIA Nemotron 3 Nano 4B — GGUF Q4 K M NVIDIA's own Q4 K M GGUF, re hosted with measured performance for the 1bit engine https://github.com/1bit MONSTER/engin…
Runs locally from ~2.64 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf | GGUF | Q4_K_M | 2.64 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/NVIDIA-Nemotron-3-Nano-4B-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | other |
| Base model | nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 |
| Last modified | 2026-09-26T15:25:22.000Z |
Model README
---
license: other
license_name: nvidia-nemotron-open-model-license
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/
base_model:
- nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
tags:
- gguf
---
NVIDIA-Nemotron-3-Nano-4B — GGUF (Q4_K_M)
NVIDIA's own Q4_K_M GGUF, re-hosted with measured performance for the
1bit engine on Strix Halo.
Licensed under the NVIDIA Nemotron Open Model License —
review the terms before commercial use.
Contents
NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 1638 tok/s · tg128: 57.6 tok/s
Running it
1bit serve -m NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf --device vulkanAttribution
- Model and quantization: nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF.
Run 1bit-MONSTER/NVIDIA-Nemotron-3-Nano-4B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models