Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,37 @@
+# uCoder-8b-base-GGUF
+
+Quantized GGUF models converted from [uaytug/uCoder-8b-base](https://huggingface.co/uaytug/uCoder-8b-base).
+
+Converted using the latest llama.cpp (CUDA-accelerated quantization).
+
+### Available Files
+
+**16-bit**
+- `uCoder-8b-base-BF16.gguf` → Highest precision float (similar to original, ~16 GB)
+
+**8-bit**
+- `uCoder-8b-base-Q8_0.gguf` → Near-lossless
+
+**6-bit**
+- `uCoder-8b-base-Q6_K.gguf`
+
+**5-bit**
+- `uCoder-8b-base-Q5_K_S.gguf`
+- `uCoder-8b-base-Q5_K_M.gguf` → Great quality
+
+**4-bit** (most popular range)
+- `uCoder-8b-base-Q4_K_M.gguf` → **Recommended balance**
+- `uCoder-8b-base-Q4_K_S.gguf`
+- `uCoder-8b-base-Q4_1.gguf`
+
+**3-bit**
+- `uCoder-8b-base-Q3_K_S.gguf`
+- `uCoder-8b-base-Q3_K_M.gguf`
+
+**2-bit**
+- `uCoder-8b-base-Q2_K.gguf`
+
+### Usage
+Use with llama.cpp, LM Studio, Ollama, etc.
+
+This is a **base** model — best for code/further fine-tuning.