Update README.md

README.md

@@ -18,6 +18,45 @@ base_model:
 - uaytug/ucoder-mini
 ---
 
+# uCoder-8b-base-GGUF
+
+Quantized GGUF models converted from [uaytug/ucoder-mini](https://huggingface.co/uaytug/ucoder-mini).
+
+Converted using the latest llama.cpp (CUDA-accelerated quantization).
+
+### Available Files
+
+**16-bit**
+- `ucoder-mini-BF16.gguf` → **Highest precision float (similar to original, ~16 GB)**
+
+**8-bit**
+- `ucoder-mini-Q8_0.gguf` → **Near-lossless**
+
+**6-bit**
+- `ucoder-mini-Q6_K.gguf`
+
+**5-bit**
+- `ucoder-mini-Q5_K_S.gguf`
+- `ucoder-mini-Q5_K_M.gguf` → **Great quality**
+
+**4-bit** (most popular range)
+- `ucoder-mini-Q4_K_M.gguf` → **Recommended balance**
+- `ucoder-mini-Q4_K_S.gguf`
+- `ucoder-mini-Q4_1.gguf`
+- `ucoder-mini-IQ4_XS.gguf`
+- `ucoder-mini-IQ4_NL.gguf`
+
+**3-bit**
+- `ucoder-mini-Q3_K_S.gguf`
+- `ucoder-mini-Q3_K_M.gguf`
+- `ucoder-mini-IQ3_XXS.gguf`
+
+**2-bit**
+- `ucoder-mini-Q2_K.gguf`
+- `ucoder-mini-IQ2_M.gguf`
+
+## Original Model Information
+
 # uCoder Mini
 
 > **Important:** The model is unable to produce accurate and high-quality answers to general knowledge, creative writing, or non-coding tasks, and to questions asked in languages other than English. The answers to your questions in these areas may not be satisfactory because this model was specifically trained for **coding and mathematical reasoning tasks** (competitive programming, LeetCode, algorithm problems, etc.).
@@ -268,7 +307,7 @@ def binary_search(arr, target):
 
 | Setup | VRAM Required | Notes |
 |-------|---------------|-------|
-| FP16/BF16 | ~4 GB | Full precision inference |
+| FP16/BF16 | ~3 GB | Full precision inference |
 
 ## Citation