---
license: llama3.3
base_model: shb777/Llama-3.3-8B-Instruct-128K
pipeline_tag: text-generation
tags:
- llama-cpp
---

# Llama 3.3 8B Instruct GGUF

> [!TIP]
> Quantized GGUF versions of [shb777/Llama-3.3-8B-Instruct-128K](https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K)
> 
> Includes fixes for full context length and chat template (Unsloth)

| Quantization | File | Use Case |
|---|---|---|
| Q8_0 | `llama-3.3-8b-instruct-q8_0.gguf` | Highest quality, largest size |
| Q6_K | `llama-3.3-8b-instruct-q6_k.gguf` | Balanced quality/size |
| Q4_K_M | `llama-3.3-8b-instruct-q4_k_m.gguf` | Smaller size, good quality |