---
license: mit
language:
  - en
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - llama
  - quantized
  - gguf
  - tq2_0
pipeline_tag: text-generation
model_creator: meta
quantization: TQ2_0
---

# LlamaLite-3B-TQ2_0 (GGUF Format)

This is a **quantized** version of `meta-llama/Llama-3.2-3B-Instruct`, using **TQ2_0** quantization for optimized performance and reduced size. The model is stored in **GGUF format** for compatibility with `llama.cpp` and other lightweight inference engines.

## Model Details

- **Base Model:** [Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
- **Quantization Type:** `TQ2_0`
- **Model Size:** ~1.52GB
- **Format:** GGUF
- **Intended Use:** Text Generation, Chatbots, AI Assistants
- **License:** MIT

## Download & Usage

### 1️⃣ Install Dependencies

```bash
pip install huggingface_hub