diff --git a/gallery/index.yaml b/gallery/index.yaml
index 964fdfa59..d19e84c37 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -2623,6 +2623,21 @@
     - filename: Qwen3-Stargate-SG1-Uncensored-Abliterated-8B.i1-Q4_K_M.gguf
       sha256: 31ec697ccebbd7928c49714b8a0ec8be747be0f7c1ad71627967d2f8fe376990
       uri: huggingface://mradermacher/Qwen3-Stargate-SG1-Uncensored-Abliterated-8B-i1-GGUF/Qwen3-Stargate-SG1-Uncensored-Abliterated-8B.i1-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  url: "github:mudler/LocalAI/gallery/qwen3-deepresearch.yaml@master"
+  name: "alibaba-nlp_tongyi-deepresearch-30b-a3b"
+  urls:
+    - https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
+    - https://huggingface.co/bartowski/Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-GGUF
+  description: |
+    We present Tongyi DeepResearch, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token. Developed by Tongyi Lab, the model is specifically designed for long-horizon, deep information-seeking tasks. Tongyi-DeepResearch demonstrates state-of-the-art performance across a range of agentic search benchmarks, including Humanity's Last Exam, BrowserComp, BrowserComp-ZH, WebWalkerQA, GAIA, xbench-DeepSearch and FRAMES.
+  overrides:
+    parameters:
+      model: Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-Q4_K_M.gguf
+  files:
+    - filename: Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-Q4_K_M.gguf
+      sha256: 1afefb3b369ea2de191f24fe8ea22cbbb7b412357902f27bd81d693dde35c2d9
+      uri: huggingface://bartowski/Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-GGUF/Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-Q4_K_M.gguf
 - &gemma3
   url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
   name: "gemma-3-27b-it"
diff --git a/gallery/qwen3-deepresearch.yaml b/gallery/qwen3-deepresearch.yaml
new file mode 100644
index 000000000..a6f771348
--- /dev/null
+++ b/gallery/qwen3-deepresearch.yaml
@@ -0,0 +1,45 @@
+---
+name: "qwen3"
+
+config_file: |
+  mmap: true
+  backend: "llama-cpp"
+  template:
+    chat_message: |
+      <|im_start|>{{if eq .RoleName "tool" }}user{{else}}{{ .RoleName }}{{end}}
+      {{ if eq .RoleName "tool" -}}
+      <tool_response>
+      {{ end -}}
+      {{ if .Content -}}
+      {{.Content }}
+      {{ end -}}
+      {{ if eq .RoleName "tool" -}}
+      </tool_response>
+      {{ end -}}
+      {{ if .FunctionCall -}}
+      <tool_call>
+      {{toJson .FunctionCall}}
+      </tool_call>
+      {{ end -}}<|im_end|>
+    function: |
+      <|im_start|>system
+      You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+      {{range .Functions}}
+      {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+      {{end}}
+      For each function call return a json object with function name and arguments
+      <|im_end|>
+      {{.Input -}}
+      <|im_start|>assistant
+    chat: |
+      {{.Input -}}
+      <|im_start|>assistant
+    completion: |
+      {{.Input}}
+  context_size: 8192
+  f16: true
+  stopwords:
+  - '<|im_end|>'
+  - '<dummy32000>'
+  - '</s>'
+  - '<|endoftext|>'