chore(gallery): add Qwen3.8 GSQ-RCO IQ3_S

Complete the existing GSQ-RCO choices with the 3.50-bit build and its
vision projector. Pin downloads and verify both SHA256 values against
Hugging Face LFS metadata and download headers.

Correct the older quality description and document variant selection.

Assisted-by: Codex:gpt-6

(cherry picked from commit 70a2bd2c21, mudler/LocalAI#12651)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

gallery/index.yaml

@@ -6476,6 +6476,7 @@
     - 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:
@@ -7173,8 +7174,8 @@
     - 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:
@@ -7207,6 +7208,47 @@
     - 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
 - name: underdog-saluki-27b-1.0
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls: