File size: 191 Bytes
158552c
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
---
license: apache-2.0
---

## Introduce

Quantizing the [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B) to f16, q2, q3, q4, q5, q6 and q8 with Llama.cpp.