diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index d8866f539..c497caf2e 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -8,6 +8,7 @@
 - Fixed Z.AI Coding Plan defaults referencing the removed GLM-5.1 model ([#8096](https://github.com/earendil-works/pi/issues/8096)).
 - Fixed repeated ambiguous truncated-response recovery being mislabeled as context overflow ([#8130](https://github.com/earendil-works/pi/issues/8130)).
 - Fixed duplicate fullscreen right-click paste in VS Code-based terminals on Windows ([#8186](https://github.com/earendil-works/pi/issues/8186)).
+- Fixed llama.cpp login guidance to direct users to `/llama` before `/model` when no local models are loaded ([#8203](https://github.com/earendil-works/pi/issues/8203)).
 
 ## [0.84.2] - 2026-08-14
 
diff --git a/packages/coding-agent/docs/llama-cpp.md b/packages/coding-agent/docs/llama-cpp.md
index 13f314c9e..bffa13f42 100644
--- a/packages/coding-agent/docs/llama-cpp.md
+++ b/packages/coding-agent/docs/llama-cpp.md
@@ -53,6 +53,8 @@ Start Pi and configure the provider:
 
 Enter the router URL and optional API key. The default URL is `http://127.0.0.1:8080`.
 
+If you start the router with `--no-models-autoload`, `/login llama.cpp` only stores the connection. Run `/llama` to load a model, then `/model` to select the loaded model for the current session.
+
 Environment variables can configure the same values without `/login`:
 
 ```bash
diff --git a/packages/coding-agent/src/modes/interactive/interactive-mode.ts b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
index 6d5e6b884..999220398 100644
--- a/packages/coding-agent/src/modes/interactive/interactive-mode.ts
+++ b/packages/coding-agent/src/modes/interactive/interactive-mode.ts
@@ -257,6 +257,12 @@ function hasDefaultModelProvider(providerId: string): providerId is keyof typeof
 	return providerId in defaultModelPerProvider;
 }
 
+function llamaCppPostLoginGuidance(actionLabel: string, loadedModelCount: number): string {
+	return loadedModelCount === 0
+		? `${actionLabel}. No llama.cpp models are loaded. Use /llama to load a model, then /model to select it.`
+		: `${actionLabel}. Use /model to select a loaded llama.cpp model, or /llama to manage models.`;
+}
+
 type LoginProviderCompletionOption = {
 	id: string;
 	name: string;
@@ -5471,7 +5477,10 @@ export class InteractiveMode {
 		if (isUnknownModel(previousModel)) {
 			const availableModels = this.session.modelRuntime.getAvailableSnapshot();
 			const providerModels = availableModels.filter((model) => model.provider === providerId);
-			if (!hasDefaultModelProvider(providerId)) {
+			// Matches LLAMA_PROVIDER_ID from extensions/llama/provider.ts; kept inline to avoid coupling interactive mode to the built-in extension.
+			if (providerId === "llama.cpp") {
+				selectionError = llamaCppPostLoginGuidance(actionLabel, providerModels.length);
+			} else if (!hasDefaultModelProvider(providerId)) {
 				selectionError = `${actionLabel}, but no default model is configured for provider "${providerId}". Use /model to select a model.`;
 			} else if (providerModels.length === 0) {
 				selectionError = `${actionLabel}, but no models are available for that provider. Use /model to select a model.`;