README.md

metadata

base_model:
  - meta-llama/Llama-3.1-8B
  - ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
tags:
  - merge
  - mergekit
  - lazymergekit
  - meta-llama/Llama-3.1-8B
  - ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
language:
  - tr
  - en

TurkLlama-Mix-v2 GGUF Quantized Models

Technical Details

• Quantization Tool: llama.cpp
• Version: version: 5106 (47ba87d0)

Model Information

• Base Model: matrixportal/TurkLlama-Mix-v2
• Quantized by: matrixportal

Available Files

🚀 Download	🔢 Type	📝 Description
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)

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