--- language: - en license: llama3.1 base_model: FuseAI/FuseChat-Llama-3.1-8B-Instruct base_model_relation: quantized library_name: mlc-llm pipeline_tag: text-generation --- 3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [FuseChat-Llama-3.1-8B-Instruct](https://huggingface.co/FuseAI/FuseChat-Llama-3.1-8B-Instruct) for inference with the [Private LLM](http://privatellm.app) app.