Update README.md

README.md

@@ -6,27 +6,29 @@ tags:
 - llama.cpp
 - quantized
 - iq4_xs
-- Imatrix
+- q5_k_m
+- q6_k
+- imatrix
 - saturated-labs
 - roleplay
 - storytelling
 - language-model
-quantization: IQ4_XS
+quantization: IQ4_XS, Q5_K_M, Q6_K
 model_type: llama
 language:
 - en
 ---
 
-# 🦖 T-Rex-mini — GGUF I1 IQ4_XS (Quantized - Imatrix)
+# 🦖 T-Rex-mini — GGUF I1 (Quantized - Imatrix)
 
-This is a **quantized GGUF version** of [`saturated-labs/T-Rex-mini`](https://huggingface.co/saturated-labs/T-Rex-mini), converted using [llama.cpp](https://github.com/ggerganov/llama.cpp) and quantized to the `IQ4_XS` format with Imatrix.
+This is a **quantized GGUF version** of [`saturated-labs/T-Rex-mini`](https://huggingface.co/saturated-labs/T-Rex-mini), converted using [llama.cpp](https://github.com/ggerganov/llama.cpp) and quantized with imatrix.
 
 ## 🔧 Quantization Details
 
 - **Original Model**: `saturated-labs/T-Rex-mini`
 - **Format**: GGUF (`.gguf`)
-- **Quantization Type**: `IQ4_XS`
+- **Quantization Type**: `IQ4_XS, Q5_K_M, Q6_K`
 - **Tool Used**: [`llama.cpp`](https://github.com/ggerganov/llama.cpp)
 - **Command**:
   ```bash
-  ./llama-quantize.exe --imatrix imatrix.dat trex-mini-f16.gguf trex-mini-iq4_xs.gguf iq4_xs
+  ./llama-quantize.exe --imatrix imatrix.dat trex-mini-f16.gguf trex-mini-QX_X_X.gguf QX_X_X