---
base_model: MoonRide/Llama-3.2-3B-Khelavaster
quantized_by: MoonRide
language:
- en
library_name: transformers
license: llama3.2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- mergekit
- merge
- chat
- moonride
---
<img src="https://huggingface.co/MoonRide/Llama-3.2-3B-Khelavaster/resolve/main/Khelavaster.jpg">

Experimental merge of multiple Llama 3.2 3B models, guided by [MoonRide-Index-v7](https://huggingface.co/datasets/MoonRide/MoonRide-LLM-Index-v7). Created with [mergekit](https://github.com/cg123/mergekit).

Original model: [MoonRide/Llama-3.2-3B-Khelavaster](https://huggingface.co/MoonRide/Llama-3.2-3B-Khelavaster/).

GGUFs made with [llama.cpp](https://github.com/ggml-org/llama.cpp) ([b4855](https://github.com/ggml-org/llama.cpp/releases/tag/b4855)). Calibration file used for creating imatrix: [calibration_datav3.txt](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).

For best quality use Q8_0 or Q6_K quant.