diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
index a5af4a904..b15745b36 100644
--- a/docs/content/features/model-gallery.md
+++ b/docs/content/features/model-gallery.md
@@ -205,6 +205,23 @@ The files use standard llama.cpp quantization types and the Apache-2.0 license.
 See the [publisher's model card](https://huggingface.co/agentionai/Qwen3.8-27B-AP-GGUF)
 for quantization details. These entries do not enable MTP speculative decoding.
 
+## Qwen3.8-27B GSQ-RCO
+
+The Qwen3.8-27B gallery group includes ISTA DASLab's IQ2_XS, IQ2_S, IQ3_XXS,
+and IQ3_S GGUF builds for llama.cpp. Each includes the BF16 vision projector.
+IQ3_S uses 3.50 bits per weight and has an 11.8 GB weights file.
+
+To select IQ3_S explicitly, run:
+
+```bash
+local-ai models install qwen3.8-27b-q4 --variant qwen3.8-27b-gsq-rco-iq3-s
+```
+
+These builds use the embedded chat template and default to 262,144 context tokens.
+They do not enable MTP speculative decoding.
+See the [publisher's model card](https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF)
+for quantization details and benchmarks.
+
 ## Swift 1.5 Qwen3.8-27B GSQ-RCO
 
 Install `swift-1.5-qwen3.8-27b-gsq-rco` for text chat with llama.cpp.
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 947b4be7d..21846f96c 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -5843,6 +5843,7 @@
     - model: qwen3.8-27b-gsq-rco-iq2-xs
     - model: qwen3.8-27b-gsq-rco-iq2-s
     - model: qwen3.8-27b-gsq-rco-iq3-xxs
+    - model: qwen3.8-27b-gsq-rco-iq3-s
     - model: qwen3.8-27b-q8
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
@@ -6381,8 +6382,8 @@
     - https://huggingface.co/Qwen/Qwen3.8-27B
     - https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
   description: |
-    Qwen3.8-27B with ISTA DASLab's recommended 3.00-bit GSQ-RCO IQ3_XXS mixed
-    quantization. The 10.1 GB model provides the highest quality in this set
+    Qwen3.8-27B with ISTA DASLab's 3.00-bit GSQ-RCO IQ3_XXS mixed
+    quantization. The 10.1 GB model offers a smaller alternative to IQ3_S
     and retains the shared BF16 vision projector.
   last_checked: "2026-08-30"
   overrides:
@@ -6415,6 +6416,47 @@
     - filename: llama-cpp/mmproj/qwen3.8-27b-gsq-rco/mmproj-Qwen3.8-27B-BF16.gguf
       uri: huggingface://ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/mmproj-Qwen3.8-27B-BF16.gguf
       sha256: 13cb7bebccbd04afc8f4090cb949ecf8937cdf7377c5799b1a0c594e7c0d3e16
+- !!merge <<: *qwen3-8-27b
+  name: qwen3.8-27b-gsq-rco-iq3-s
+  variants: []
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.8-27B
+    - https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
+  description: |
+    Qwen3.8-27B with ISTA DASLab's recommended 3.50-bit GSQ-RCO IQ3_S mixed
+    quantization. The 11.8 GB model retains the shared BF16 vision projector
+    for image input and uses the embedded chat template with llama.cpp.
+  last_checked: "2026-10-12"
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/qwen3.8-27b-gsq-rco/mmproj-Qwen3.8-27B-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/qwen3.8-27b-gsq-rco/Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
+      presence_penalty: 0
+      repeat_penalty: 1
+      temperature: 1
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/qwen3.8-27b-gsq-rco/Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
+      uri: https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d562806dbafae37109975e970aae91b43e73b440/Qwen3.8-27B-GSQ-RCO-IQ3_S.gguf
+      sha256: 64b53b64c7aa39f20a7e54bd80582fe595b1d745624ee8a72e92508c0326d810
+    - filename: llama-cpp/mmproj/qwen3.8-27b-gsq-rco/mmproj-Qwen3.8-27B-BF16.gguf
+      uri: https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/resolve/d562806dbafae37109975e970aae91b43e73b440/mmproj-Qwen3.8-27B-BF16.gguf
+      sha256: 13cb7bebccbd04afc8f4090cb949ecf8937cdf7377c5799b1a0c594e7c0d3e16
 - &spark-x2-5-1-7b
   name: spark-x2.5-1.7b-q4
   url: github:mudler/LocalAI/gallery/virtual.yaml@master