diff --git a/src/any_llm/providers/ollama/ollama.py b/src/any_llm/providers/ollama/ollama.py
index db313d32e..88d75a085 100644
--- a/src/any_llm/providers/ollama/ollama.py
+++ b/src/any_llm/providers/ollama/ollama.py
@@ -1,6 +1,6 @@
 import json
 import os
-from collections.abc import AsyncIterator, Iterator
+from collections.abc import AsyncIterator, Iterator, Sequence
 from typing import Any
 
 try:
@@ -8,6 +8,7 @@
     from ollama import ChatResponse as OllamaChatResponse
 
     from any_llm.providers.ollama.utils import (
+        _convert_models_list,
         _create_chat_completion_from_ollama_response,
         _create_openai_chunk_from_ollama_chunk,
         _create_openai_embedding_response_from_ollama,
@@ -21,6 +22,7 @@
 
 from any_llm.provider import ApiConfig, Provider
 from any_llm.types.completion import ChatCompletion, ChatCompletionChunk, CompletionParams, CreateEmbeddingResponse
+from any_llm.types.model import Model
 
 
 class OllamaProvider(Provider):
@@ -40,7 +42,7 @@ class OllamaProvider(Provider):
     SUPPORTS_RESPONSES = False
     SUPPORTS_COMPLETION_REASONING = True
     SUPPORTS_EMBEDDING = True
-    SUPPORTS_LIST_MODELS = False
+    SUPPORTS_LIST_MODELS = True
 
     PACKAGES_INSTALLED = PACKAGES_INSTALLED
 
@@ -248,3 +250,11 @@ def embedding(
             **kwargs,
         )
         return _create_openai_embedding_response_from_ollama(response)
+
+    def list_models(self, **kwargs: Any) -> Sequence[Model]:
+        """
+        Fetch available models from the /v1/models endpoint.
+        """
+        client = Client(host=self.url, timeout=kwargs.pop("timeout", None))
+        models_list = client.list(**kwargs)
+        return _convert_models_list(models_list)
diff --git a/src/any_llm/providers/ollama/utils.py b/src/any_llm/providers/ollama/utils.py
index dcc43a440..469d0e044 100644
--- a/src/any_llm/providers/ollama/utils.py
+++ b/src/any_llm/providers/ollama/utils.py
@@ -5,6 +5,7 @@
 
 from ollama import ChatResponse as OllamaChatResponse
 from ollama import EmbedResponse
+from ollama import ListResponse as OllamaListResponse
 from ollama import Message as OllamaMessage
 
 from any_llm.types.completion import (
@@ -25,6 +26,7 @@
     Reasoning,
     Usage,
 )
+from any_llm.types.model import Model
 
 
 def _create_openai_embedding_response_from_ollama(
@@ -203,3 +205,16 @@ def _create_chat_completion_from_ollama_response(response: OllamaChatResponse) -
         choices=[choice],
         usage=usage,
     )
+
+
+def _convert_models_list(models_list: OllamaListResponse) -> list[Model]:
+    models = models_list.models
+    return [
+        Model(
+            id=model.model or "Unknown",
+            object="model",
+            created=int(model.modified_at.timestamp()) if model.modified_at else 0,
+            owned_by="ollama",
+        )
+        for model in models
+    ]