apps/librechat/release.yaml

@@ -64,7 +64,9 @@ spec:
               baseURL: "http://llama.llama.svc.cluster.local:11434/v1/chat/completions"
               models:
                 default: [
-                  "DeepSeek-R1-0528-Qwen3-8B-GGUF"
+                  "DeepSeek-R1-0528-Qwen3-8B-GGUF",
+                  "Qwen3-8B-GGUF",
+                  "Qwen3-8B-GGUF-Q6_K"
                 ]
               titleConvo: true
               titleModel: "current_model"

apps/llama/configmap.yaml

@@ -12,3 +12,15 @@ data:
           -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M
           -ngl 37
           --port ${PORT}
+      "Qwen3-8B-GGUF":
+        cmd: |
+          /app/llama-server
+          -hf unsloth/Qwen3-8B-GGUF:Q4_K_M
+          -ngl 37
+          --port ${PORT}
+      "Qwen3-8B-GGUF-Q6_K":
+        cmd: |
+          /app/llama-server
+          -hf unsloth/Qwen3-8B-GGUF:Q6_K
+          -ngl 37
+          --port ${PORT}