---
license: other
base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
tags:
  - gguf
  - quantized
  - apex
  - moe
  - mixture-of-experts
  - nvidia
  - nemotron
  - mamba
  - hybrid
---

# Nemotron-3-Nano-30B-A3B APEX GGUF

**APEX (Adaptive Precision for EXpert Models)** quantizations of [NVIDIA-Nemotron-3-Nano-30B-A3B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16).

**Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team** | [APEX Project](https://github.com/mudler/apex-quant) | [Technical Report](https://github.com/mudler/apex-quant/blob/main/paper/APEX_Technical_Report.pdf)

## Benchmark Results

Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see [mudler/Qwen3.5-35B-A3B-APEX-GGUF](https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF).

## What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

See the [APEX project](https://github.com/mudler/apex-quant) for full details, technical report, and scripts.

## Architecture

- **Model**: NVIDIA-Nemotron-3-Nano-30B-A3B (NemotronH)
- **Layers**: 52 (23 Mamba-2, 23 MoE, 6 GQA attention)
- **Experts**: 128 routed + 1 shared (6 active per token)
- **Total Parameters**: 30B
- **Active Parameters**: ~3.5B per token
- **APEX Config**: 5+5 symmetric edge gradient across 52 layers

## Run with LocalAI

```bash
local-ai run mudler/Nemotron-3-Nano-30B-A3B-APEX-GGUF@Nemotron-3-Nano-30B-A3B-APEX-I-Balanced.gguf
```

## Credits

APEX is brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. Developed through human-driven, AI-assisted research. Built on [llama.cpp](https://github.com/ggerganov/llama.cpp).