---
base_model: gradientai/Llama-3-8B-Instruct-Gradient-1048k
inference: false
language:
- en
license: llama3
model_name: Llama-3-8B-Instruct-Gradient-1048k
pipeline_tag: text-generation
tags:
- meta
- llama-3
- quantized

---

# Llama-3-8B-Instruct-Gradient-1048k-GGUF

Quantized Llama-3-8B-Instruct-Gradient-1048k models using recent versions of llama.cpp.