Update Dockerfile

Dockerfile

@@ -26,6 +26,9 @@ RUN wget "https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF/resolve/main/mmproj-B
 # --- MODEL 6: GPT OSS 20B ---
 RUN wget "https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-Q4_0.gguf" -O /models/gpt-oss-20b-Q4_0.gguf
 
+# --- MODEL 7: Gemma 4 12B IT ---
+RUN wget "https://huggingface.co/unsloth/gemma-4-12b-it-GGUF/resolve/main/gemma-4-12b-it-Q4_K_M.gguf" -O /models/gemma-4-12b-it-Q4_K_M.gguf
+
 # --- CREATE ROUTER CONFIGURATION ---
 RUN echo "[gemma-4-E2B-it-vision]" > /models.ini && \
     echo "model = /models/gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf" >> /models.ini && \
@@ -62,6 +65,11 @@ RUN echo "[gemma-4-E2B-it-vision]" > /models.ini && \
     echo "[gpt-oss-20b]" >> /models.ini && \
     echo "model = /models/gpt-oss-20b-Q4_0.gguf" >> /models.ini && \
     echo "ctx-size = 32768" >> /models.ini && \
+    echo "flash-attn = on" >> /models.ini && \
+    echo "" >> /models.ini && \
+    echo "[gemma-4-12b]" >> /models.ini && \
+    echo "model = /models/gemma-4-12b-it-Q4_K_M.gguf" >> /models.ini && \
+    echo "ctx-size = 131072" >> /models.ini && \
     echo "flash-attn = on"
 
 # --- START SERVER IN ROUTER MODE WITH CORS, TOOLS & MCP ENABLED ---