diff --git a/frontend/src/views/SettingsView.vue b/frontend/src/views/SettingsView.vue
index dd1b408..32a2722 100644
--- a/frontend/src/views/SettingsView.vue
+++ b/frontend/src/views/SettingsView.vue
@@ -15,6 +15,7 @@ const toastStore = useToastStore();
 const pushStore = usePushStore();
 const assistantName = ref("");
 const defaultModel = ref("");
+const backgroundModel = ref("");
 const installedModels = ref<string[]>([]);
 const defaultChatModel = ref("");
 
@@ -708,6 +709,7 @@ onMounted(async () => {
   // Load notification preferences from user settings
   const allSettings = await apiGet<Record<string, string>>("/api/settings");
   defaultModel.value = allSettings.default_model ?? "";
+  backgroundModel.value = allSettings.background_model ?? "";
   chatRetentionDays.value = allSettings.chat_retention_days !== undefined
     ? Number(allSettings.chat_retention_days)
     : 90;
@@ -929,6 +931,7 @@ async function saveAssistant() {
     await store.updateSettings({
       assistant_name: assistantName.value.trim() || "Fable",
       default_model: defaultModel.value,
+      background_model: backgroundModel.value,
     });
     saved.value = true;
     setTimeout(() => (saved.value = false), 2000);
@@ -1437,6 +1440,20 @@ function formatUserDate(iso: string): string {
             </select>
             <p class="field-hint">Model used for new conversations.</p>
           </div>
+          <div class="field">
+            <label for="background-model">Background Model</label>
+            <select id="background-model" v-model="backgroundModel" class="input">
+              <option value="">Default (qwen2.5:0.5b)</option>
+              <option v-for="m in installedModels" :key="m" :value="m">{{ m }}</option>
+            </select>
+            <p class="field-hint">
+              Model used for background tasks: title generation, tag suggestions, project summaries, and RSS classification.
+              Using a small dedicated model (e.g. qwen2.5:0.5b) keeps the chat model's KV cache warm between messages, significantly reducing response time.
+              <span v-if="backgroundModel && backgroundModel === (defaultModel || defaultChatModel)" class="field-hint-warn">
+                ⚠ Setting this to the same model as Chat Model will wipe the KV cache after every background task, increasing response latency.
+              </span>
+            </p>
+          </div>
         </div>
         <div class="actions">
           <button class="btn-save" @click="saveAssistant" :disabled="saving">
@@ -3078,6 +3095,11 @@ FABLE_API_KEY=&lt;your-api-key&gt;</pre>
   font-size: 0.78rem;
   color: var(--color-text-muted);
 }
+.field-hint-warn {
+  display: block;
+  margin-top: 0.3rem;
+  color: #f59e0b;
+}
 .actions {
   display: flex;
   align-items: center;
diff --git a/src/fabledassistant/services/chat.py b/src/fabledassistant/services/chat.py
index 698bc0e..b8175bc 100644
--- a/src/fabledassistant/services/chat.py
+++ b/src/fabledassistant/services/chat.py
@@ -9,6 +9,7 @@ from fabledassistant.models.conversation import Conversation, Message
 from fabledassistant.config import Config
 from fabledassistant.services.llm import generate_completion
 from fabledassistant.services.notes import create_note
+from fabledassistant.services.settings import get_setting
 
 logger = logging.getLogger(__name__)
 
@@ -234,7 +235,8 @@ async def save_response_as_note(user_id: int, message_id: int) -> dict:
                 },
                 {"role": "user", "content": msg.content[:2000]},
             ]
-            title = await generate_completion(prompt_messages, Config.OLLAMA_BACKGROUND_MODEL)
+            bg_model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
+            title = await generate_completion(prompt_messages, bg_model)
             title = title.strip().strip('"\'').strip()[:100]
         except Exception:
             logger.warning("Failed to generate note title, using fallback", exc_info=True)
diff --git a/src/fabledassistant/services/generation_task.py b/src/fabledassistant/services/generation_task.py
index fbb19e9..f757b97 100644
--- a/src/fabledassistant/services/generation_task.py
+++ b/src/fabledassistant/services/generation_task.py
@@ -24,6 +24,7 @@ from fabledassistant.services.generation_buffer import (
 )
 from fabledassistant.services.llm import ChatChunk, build_context, generate_completion, stream_chat, stream_chat_with_tools, summarize_history_for_context
 from fabledassistant.services.chat import update_conversation_title
+from fabledassistant.services.settings import get_setting
 from fabledassistant.services.logging import log_generation
 from fabledassistant.services.tools import get_tools_for_user, execute_tool
 from fabledassistant.services.research import run_research_pipeline
@@ -116,7 +117,7 @@ _TOOL_LABELS: dict[str, str] = {
 }
 
 
-async def _generate_title(messages: list[dict], model: str) -> str:
+async def _generate_title(messages: list[dict], user_id: int) -> str:
     """Ask the LLM for a concise conversation title."""
     # Build conversation text like summarize_conversation_as_note
     conv_lines = []
@@ -138,7 +139,8 @@ async def _generate_title(messages: list[dict], model: str) -> str:
         },
         {"role": "user", "content": "\n\n".join(conv_lines)},
     ]
-    title = await generate_completion(prompt_messages, Config.OLLAMA_BACKGROUND_MODEL, max_tokens=30)
+    bg_model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
+    title = await generate_completion(prompt_messages, bg_model, max_tokens=30)
     title = title.strip().strip('"\'').strip()
     return title[:100] if title else ""
 
@@ -483,7 +485,7 @@ async def run_generation(
 
             async def _bg_title() -> None:
                 try:
-                    title = await _generate_title(title_messages, model)
+                    title = await _generate_title(title_messages, user_id)
                     if title:
                         await update_conversation_title(user_id, conv_id, title)
                 except Exception:
diff --git a/src/fabledassistant/services/projects.py b/src/fabledassistant/services/projects.py
index 799ad50..a2ce5af 100644
--- a/src/fabledassistant/services/projects.py
+++ b/src/fabledassistant/services/projects.py
@@ -121,8 +121,10 @@ async def generate_project_summary(user_id: int, project_id: int) -> None:
 
         from fabledassistant.services.llm import generate_completion
         from fabledassistant.config import Config
+        from fabledassistant.services.settings import get_setting
         messages = [{"role": "user", "content": prompt}]
-        summary = await generate_completion(messages, model=Config.OLLAMA_BACKGROUND_MODEL, max_tokens=400)
+        bg_model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
+        summary = await generate_completion(messages, model=bg_model, max_tokens=400)
         if not summary:
             return
 
diff --git a/src/fabledassistant/services/rss_classifier.py b/src/fabledassistant/services/rss_classifier.py
index a9402ca..00934cc 100644
--- a/src/fabledassistant/services/rss_classifier.py
+++ b/src/fabledassistant/services/rss_classifier.py
@@ -122,7 +122,7 @@ async def classify_and_store(
     except Exception:
         include_topics = []
 
-    model = await get_setting(user_id, "default_model", Config.OLLAMA_MODEL)
+    model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
 
     # Classify in batches of 10
     batch_size = 10
diff --git a/src/fabledassistant/services/tag_suggestions.py b/src/fabledassistant/services/tag_suggestions.py
index 6ae0e5e..b39a622 100644
--- a/src/fabledassistant/services/tag_suggestions.py
+++ b/src/fabledassistant/services/tag_suggestions.py
@@ -7,6 +7,7 @@ import re
 from fabledassistant.config import Config
 from fabledassistant.services.llm import generate_completion
 from fabledassistant.services.notes import get_all_tags
+from fabledassistant.services.settings import get_setting
 
 logger = logging.getLogger(__name__)
 
@@ -21,7 +22,7 @@ async def suggest_tags(user_id: int, title: str, body: str, current_tags: list[s
         return []
 
     existing_tags = await get_all_tags(user_id)
-    model = Config.OLLAMA_BACKGROUND_MODEL
+    model = await get_setting(user_id, "background_model", Config.OLLAMA_BACKGROUND_MODEL)
 
     existing_list = ", ".join(f"#{t}" for t in existing_tags) if existing_tags else "(none yet)"