---
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
license: llama3.2
base_model: NousResearch/Hermes-3-Llama-3.2-3B
base_model_relation: quantized
library_name: mlc-llm
pipeline_tag: text-generation
tags:
- Llama-3
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- roleplaying
- chat
---

4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B) for inference with [Private LLM](http://privatellm.app).