diff --git a/apps/mana/apps/web/src/lib/modules/memoro/views/DetailView.svelte b/apps/mana/apps/web/src/lib/modules/memoro/views/DetailView.svelte
index b412fedde..6ece01255 100644
--- a/apps/mana/apps/web/src/lib/modules/memoro/views/DetailView.svelte
+++ b/apps/mana/apps/web/src/lib/modules/memoro/views/DetailView.svelte
@@ -15,13 +15,13 @@
 
 	// Human-readable labels for the title-source badge below the title
 	// input. We use these specific strings (not @mana/shared-llm's
-	// generic tierLabel) so we can surface the actual model name where
-	// known — "gemma3:4b" for mana-server, "Gemma 4" for browser tier
-	// — rather than the abstract tier name.
+	// generic tierLabel) so we can surface the actual model family
+	// — both browser and mana-server now run Gemma 4 variants, so the
+	// label stays coherent across tiers.
 	const TITLE_SOURCE_LABELS: Record<LlmTier, string> = {
 		none: 'Lokal (regelbasiert)',
-		browser: 'Auf deinem Gerät (Gemma 4)',
-		'mana-server': 'Mana-Server (gemma3:4b)',
+		browser: 'Auf deinem Gerät (Gemma 4 E2B)',
+		'mana-server': 'Mana-Server (Gemma 4 E4B)',
 		cloud: 'Google Gemini',
 	};
 
diff --git a/packages/shared-llm/src/backends/mana-server.ts b/packages/shared-llm/src/backends/mana-server.ts
index 652c7969d..474279e54 100644
--- a/packages/shared-llm/src/backends/mana-server.ts
+++ b/packages/shared-llm/src/backends/mana-server.ts
@@ -2,18 +2,27 @@
  * Mana-server backend — calls services/mana-llm with an Ollama model
  * string. mana-llm's ProviderRouter recognizes plain Ollama model names
  * (no provider prefix) and routes them to the local Ollama instance on
- * the Mac Mini, with automatic Gemini fallback if Ollama is overloaded.
+ * the Mac Mini (running on the M4's Metal GPU), with automatic Gemini
+ * fallback if Ollama is overloaded.
  *
- * The default model is gemma3:4b — same model family as the browser
- * tier (Gemma 4 E2B is the smaller sibling), so prompts behave
- * consistently when a task auto-falls between tiers.
+ * The default model is gemma4:e4b — Google's Gemma 4 "Effective 4B"
+ * variant, released 2026-04-02. Same family as @mana/local-llm's
+ * browser tier model (Gemma 4 E2B is the smaller sibling) so prompts
+ * behave consistently when a task auto-falls between tiers. e4b is
+ * the right Mana-Server default because:
+ *   - 9.6 GB on disk fits comfortably on the M4's 16 GB unified memory
+ *   - 128K context window covers all current title/summarize tasks
+ *   - The "Effective 4B" architecture punches well above its weight
+ *     class (better than gemma3:4b on most German prompts)
+ *   - The tier name we surface in the source label stays "Gemma 4"
+ *     family for both browser and mana-server, so the UX is coherent
  */
 
 import type { GenerateResult, LlmBackend, LlmTaskRequest } from '../types';
 import { callManaLlmStreaming, resolveLlmBaseUrl } from './remote';
 
 export interface ManaServerBackendOptions {
-	/** Ollama model name to send to mana-llm. Default 'gemma3:4b'. */
+	/** Ollama model name to send to mana-llm. Default 'gemma4:e4b'. */
 	defaultModel?: string;
 }
 
@@ -22,7 +31,7 @@ export class ManaServerBackend implements LlmBackend {
 	private readonly defaultModel: string;
 
 	constructor(opts: ManaServerBackendOptions = {}) {
-		this.defaultModel = opts.defaultModel ?? 'gemma3:4b';
+		this.defaultModel = opts.defaultModel ?? 'gemma4:e4b';
 	}
 
 	isAvailable(): boolean {