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-Test GGUF Quantized Models

Technical Details

Quantization Tool: llama.cpp
Version: version: 5143 (b43d89e3)

Model Information

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

Available Files

🚀 Download	🔢 Type	📝 Description
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)

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