diff --git a/packages/tasks/src/local-apps.spec.ts b/packages/tasks/src/local-apps.spec.ts
index f4ec4bca47..06553c97c8 100644
--- a/packages/tasks/src/local-apps.spec.ts
+++ b/packages/tasks/src/local-apps.spec.ts
@@ -13,7 +13,7 @@ describe("local-apps", () => {
 		const snippet = snippetFunc(model);
 
 		expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
+llama-server -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
 	});
 
 	it("llama.cpp non-conversational", async () => {
@@ -26,8 +26,7 @@ llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
 		const snippet = snippetFunc(model);
 
 		expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli -hf mlabonne/gemma-2b-GGUF:{{QUANT_TAG}} \\
-  -p "Once upon a time,"`);
+llama-server -hf mlabonne/gemma-2b-GGUF:{{QUANT_TAG}}`);
 	});
 
 	it("vLLM conversational llm", async () => {
diff --git a/packages/tasks/src/local-apps.ts b/packages/tasks/src/local-apps.ts
index af2f798d12..c7e92efc18 100644
--- a/packages/tasks/src/local-apps.ts
+++ b/packages/tasks/src/local-apps.ts
@@ -108,23 +108,18 @@ function getQuantTag(filepath?: string): string {
 const snippetLlamacpp = (model: ModelData, filepath?: string): LocalAppSnippet[] => {
 	const command = (binary: string) => {
 		const snippet = ["# Load and run the model:", `${binary} -hf ${model.id}${getQuantTag(filepath)}`];
-		if (!model.tags.includes("conversational")) {
-			// for non-conversational models, add a prompt
-			snippet[snippet.length - 1] += " \\";
-			snippet.push('  -p "Once upon a time,"');
-		}
 		return snippet.join("\n");
 	};
 	return [
 		{
 			title: "Install from brew",
 			setup: "brew install llama.cpp",
-			content: command("llama-cli"),
+			content: command("llama-server"),
 		},
 		{
 			title: "Install from WinGet (Windows)",
 			setup: "winget install llama.cpp",
-			content: command("llama-cli"),
+			content: command("llama-server"),
 		},
 		{
 			title: "Use pre-built binary",
@@ -133,17 +128,17 @@ const snippetLlamacpp = (model: ModelData, filepath?: string): LocalAppSnippet[]
 				"# Download pre-built binary from:",
 				"# https://github.com/ggerganov/llama.cpp/releases",
 			].join("\n"),
-			content: command("./llama-cli"),
+			content: command("./llama-server"),
 		},
 		{
 			title: "Build from source code",
 			setup: [
 				"git clone https://github.com/ggerganov/llama.cpp.git",
 				"cd llama.cpp",
-				"cmake -B build -DLLAMA_CURL=ON",
-				"cmake --build build -j --target llama-cli",
+				"cmake -B build",
+				"cmake --build build -j --target llama-server",
 			].join("\n"),
-			content: command("./build/bin/llama-cli"),
+			content: command("./build/bin/llama-server"),
 		},
 	];
 };