Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model: google/gemma-3-270m-it
+language:
+- tr
+- en
+library_name: transformers
+license: apache-2.0
+tags:
+- matrixportal
+inference: false
+---
+
+# gemma-3-270m-it-tr GGUF Quantized Models
+
+## Technical Details
+- **Quantization Tool:** llama.cpp
+- **Version:** version: 6314 (a8bca68f)
+
+## Model Information
+- **Base Model:** [matrixportalx/gemma-3-270m-it-tr](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr)
+- **Quantized by:** [matrixportalx](https://huggingface.co/matrixportalx)
+
+## Available Files
+| 🚀 Download | 🔢 Type | 📝 Description |
+|------------|---------|---------------|
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q2_k.gguf) | Q2 K | Tiny size, lowest quality (emergency use only) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q3_k_s.gguf) | Q3 K S | Very small, low quality (basic tasks) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q3_k_m.gguf) | Q3 K M | Small, acceptable quality |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q3_k_l.gguf) | Q3 K L | Small, better than Q3_K_M (good for low RAM) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q4_k_s.gguf) | Q4 K S | 4-bit optimized (good space savings) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q5_0.gguf) | Q5 0 | 5-bit high quality |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q5_k_s.gguf) | Q5 K S | 5-bit optimized |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q6_k.gguf) | Q6 K | 6-bit near-perfect (premium quality) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.q8_0.gguf) | Q8 0 | 8-bit maximum (overkill for most) |
+| [Download](https://huggingface.co/matrixportalx/gemma-3-270m-it-tr-GGUF/resolve/main/gemma-3-270m-it-tr.f16.gguf) | F16 | Full precision (maximum accuracy) |
+
+💡 **Q4 K M** provides the best balance for most use cases