| base_model: matrixportal/Turkce-LLM | |
| language: | |
| - tr | |
| - en | |
| library_name: transformers | |
| license: apache-2.0 | |
| tags: | |
| - matrixportal | |
| inference: false | |
| # Metafor GGUF Quantized Models | |
| ## Technical Details | |
| - **Quantization Tool:** llama.cpp | |
| - **Version:** version: 5170 (658987cf) | |
| ## Model Information | |
| - **Base Model:** [matrixportal/Metafor](https://huggingface.co/matrixportal/Metafor) | |
| - **Quantized by:** [matrixportal](https://huggingface.co/matrixportal) | |
| ## Available Files | |
| | 🚀 Download | 🔢 Type | 📝 Description | | |
| |------------|---------|---------------| | |
| | [Download](https://huggingface.co/matrixportal/Metafor-GGUF/resolve/main/metafor.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) | | |
| | [Download](https://huggingface.co/matrixportal/Metafor-GGUF/resolve/main/metafor.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) | | |
| | [Download](https://huggingface.co/matrixportal/Metafor-GGUF/resolve/main/metafor.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) | | |
| 💡 **Q4 K M** provides the best balance for most use cases |