diff --git a/gallery/index.yaml b/gallery/index.yaml
index d54fc8a582d6..7d4dd81b0070 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,41 @@
 ---
+- name: "glm-4.7-reap-268b-a32b"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/mradermacher/GLM-4.7-REAP-268B-A32B-GGUF
+  description: |
+    **Model Name:** GLM-4.7-REAP-268B-A32B
+    **Base Model:** `cerebras/GLM-4.7-REAP-268B-A32B`
+    **Quantization:** Q2_K (98.2 GB), Q4_K_S (152.7 GB)
+    **Format:** GGUF
+    **Use Cases:** Text generation, understanding, and reasoning.
+    **Optimization:** Efficient for deployment with low memory requirements.
+    **Features:**
+      - Based on the original GLM-4.7 model.
+      - Quantized for efficiency (Q2_K and Q4_K_S).
+      - Supports multi-part file concatenation.
+      - Optimized for speed and performance.
+
+    This model is a quantized version of the original GLM-4.7, tailored for efficient deployment with minimal memory usage.
+  overrides:
+    parameters:
+      model: llama-cpp/models/GLM-4.7-REAP-268B-A32B.Q4_K_M.gguf
+    name: GLM-4.7-REAP-268B-A32B-GGUF
+    backend: llama-cpp
+    template:
+      use_tokenizer_template: true
+    known_usecases:
+      - chat
+    function:
+      grammar:
+        disable: true
+    description: Imported from https://huggingface.co/mradermacher/GLM-4.7-REAP-268B-A32B-GGUF
+    options:
+      - use_jinja:true
+  files:
+    - filename: llama-cpp/models/GLM-4.7-REAP-268B-A32B.Q4_K_M.gguf
+      sha256: fdf2d9293b70b361ec9a78bb39d78cfc09a197993f4345bd916d353c4a55120c
+      uri: https://huggingface.co/mradermacher/GLM-4.7-REAP-268B-A32B-GGUF/resolve/main/GLM-4.7-REAP-268B-A32B.Q4_K_M.gguf
 - &qwen-tts
   urls:
     - https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice