metadata

base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct
  - atasoglu/Turkish-Llama-3-8B-function-calling
  - matrixportal/Turkish-Llama3-8B-Merged
library_name: transformers
tags:
  - mergekit
  - merge
language:
  - tr
  - en

Llama3-Turkish GGUF Quantized Models

Technical Details

Quantization Tool: llama.cpp
Version: version: 5147 (7a395f67)

Model Information

Base Model: matrixportal/Llama3-Turkish
Quantized by: matrixportal

Available Files

🚀 Download	🔢 Type	📝 Description
Download	Q2 K	Tiny size, lowest quality (emergency use only)
Download	Q3 K M	Small, acceptable quality
Download	Q4 0	Standard 4-bit (fast on ARM)
Download	Q4 K M	4-bit balanced (recommended default)
Download	Q5 K M	5-bit best (recommended HQ option)
Download	Q6 K	6-bit near-perfect (premium quality)
Download	Q8 0	8-bit maximum (overkill for most)
Download	F16	Full precision (maximum accuracy)

💡 Q4 K M provides the best balance for most use cases