---
language:
- en
license: llama3
base_model: TsinghuaC3I/Llama-3.1-8B-UltraMedical
base_model_relation: quantized
library_name: mlc-llm
pipeline_tag: text-generation
---

3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Llama-3.1-8B-UltraMedical](https://huggingface.co/TsinghuaC3I/Llama-3.1-8B-UltraMedical) for inference with the [Private LLM](http://privatellm.app) app.