diff --git a/python/samples/concepts/README.md b/python/samples/concepts/README.md
index bfde792aed39..58fd85dd6b59 100644
--- a/python/samples/concepts/README.md
+++ b/python/samples/concepts/README.md
@@ -163,13 +163,14 @@
 
 - [Grounded](./grounding/grounded.py)
 
-### Local Models - Using the [`OpenAI connector`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/open_ai/services/open_ai_chat_completion.py) and [`OnnxGenAI connector`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/onnx/services/onnx_gen_ai_chat_completion.py) to talk to models hosted locally in Ollama, OnnxGenAI, and LM Studio
+### Local Models - Using the [`OpenAI connector`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/open_ai/services/open_ai_chat_completion.py), [`Ollama connector`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/ollama/services/ollama_chat_completion.py) and [`OnnxGenAI connector`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/onnx/services/onnx_gen_ai_chat_completion.py) to talk to models hosted locally in Ollama, llmman, OnnxGenAI, and LM Studio
 
 - [ONNX Chat Completion](./local_models/onnx_chat_completion.py)
 - [LM Studio Text Embedding](./local_models/lm_studio_text_embedding.py)
 - [LM Studio Chat Completion](./local_models/lm_studio_chat_completion.py)
 - [ONNX Phi3 Vision Completion](./local_models/onnx_phi3_vision_completion.py)
 - [Ollama Chat Completion](./local_models/ollama_chat_completion.py)
+- [llmman Chat Completion](./local_models/llmman_chat_completion.py)
 - [ONNX Text Completion](./local_models/onnx_text_completion.py)
 
 ### Logging - Showing how to set up logging
diff --git a/python/samples/concepts/local_models/llmman_chat_completion.py b/python/samples/concepts/local_models/llmman_chat_completion.py
new file mode 100644
index 000000000000..7b1012558da8
--- /dev/null
+++ b/python/samples/concepts/local_models/llmman_chat_completion.py
@@ -0,0 +1,77 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+
+import asyncio
+
+from semantic_kernel.connectors.ai.ollama import OllamaChatCompletion
+from semantic_kernel.contents.chat_history import ChatHistory
+from semantic_kernel.functions.kernel_arguments import KernelArguments
+from semantic_kernel.kernel import Kernel
+
+# This concept sample shows how to use the Ollama connector with a local model
+# running in llmman (https://github.com/llmmanorg/llmman), which serves the
+# Ollama API on port 17434, so only the host differs.
+# Requires `pip install "semantic-kernel[ollama]"`. Install llmman per its
+# README, then run `llmman serve` and `llmman pull gemma4`.
+
+system_message = """
+You are a chat bot. Your name is Mosscap and
+you have one goal: figure out what people need.
+Your full name, should you need to know it, is
+Splendid Speckled Mosscap. You communicate
+effectively, but you tend to answer with long
+flowery prose.
+"""
+
+kernel = Kernel()
+
+service_id = "local-gpt"
+
+kernel.add_service(OllamaChatCompletion(service_id=service_id, ai_model_id="gemma4", host="http://localhost:17434"))
+
+settings = kernel.get_prompt_execution_settings_from_service_id(service_id)
+# Model specific settings go in the options dictionary, same as with Ollama.
+settings.options = {"num_predict": 2000, "temperature": 0.7, "top_p": 0.8}
+
+chat_function = kernel.add_function(
+    plugin_name="ChatBot",
+    function_name="Chat",
+    prompt="{{$chat_history}}{{$user_input}}",
+    template_format="semantic-kernel",
+    prompt_execution_settings=settings,
+)
+
+chat_history = ChatHistory(system_message=system_message)
+chat_history.add_user_message("Hi there, who are you?")
+chat_history.add_assistant_message("I am Mosscap, a chat bot. I'm trying to figure out what people need")
+
+
+async def chat() -> bool:
+    try:
+        user_input = input("User:> ")
+    except KeyboardInterrupt:
+        print("\n\nExiting chat...")
+        return False
+    except EOFError:
+        print("\n\nExiting chat...")
+        return False
+
+    if user_input == "exit":
+        print("\n\nExiting chat...")
+        return False
+
+    answer = await kernel.invoke(chat_function, KernelArguments(user_input=user_input, chat_history=chat_history))
+    chat_history.add_user_message(user_input)
+    chat_history.add_assistant_message(str(answer))
+    print(f"Mosscap:> {answer}")
+    return True
+
+
+async def main() -> None:
+    chatting = True
+    while chatting:
+        chatting = await chat()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())