diff --git a/README.md b/README.md
index 36d910e..82cd12a 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,10 @@ Running the LLM on every article from every feed doesn't scale locally. Instead:
 1. Every new article is embedded (`nomic-embed-text` by default) and scored against your
    preference-profile embedding — cheap, runs on all of them.
 2. Only articles above `EMBEDDING_SHORTLIST_THRESHOLD` (`crates/web/src/server/pipeline.rs`)
-   go to the LLM (`llama3.1` by default) for an actual relevance judgment with a rationale.
+   go to the LLM (`gemma4-e4b` by default — chosen because it's already pulled locally and a
+   reasonable size/speed tradeoff for a call made once per shortlisted article on every
+   pipeline run; swap it in `crates/web/src/server.rs` for a bigger/smaller model as needed)
+   for an actual relevance judgment with a rationale.
 3. `feedsignal_core::scoring::score_article` blends LLM score (dominant when present),
    embedding score (fallback / floor), and topic affinity (bounded nudge) into `final_score`,
    which is what the UI ranks by.
@@ -82,7 +85,7 @@ Requires [Ollama](https://ollama.com) running locally with the models pulled:
 
 ```sh
 ollama pull nomic-embed-text
-ollama pull llama3.1
+ollama pull gemma4-e4b
 ```
 
 And the [Dioxus CLI](https://dioxuslabs.com/learn/0.7/getting_started/) (`dx`) to build/serve
diff --git a/crates/web/src/server.rs b/crates/web/src/server.rs
index ab5ea52..5291986 100644
--- a/crates/web/src/server.rs
+++ b/crates/web/src/server.rs
@@ -23,8 +23,8 @@ async fn ensure_background_jobs_started(db: Arc<Db>) {
     BACKGROUND_JOBS
         .get_or_init(|| async {
             // TODO: move base_url/model names to config/env once there's a
-            // settings story; hardcoded to the common local Ollama defaults.
-            let llm = Arc::new(Llm::new("http://localhost:11434", "nomic-embed-text", 768, "llama3.1").expect("failed to construct ollama client"));
+            // settings story; hardcoded to models already pulled locally.
+            let llm = Arc::new(Llm::new("http://localhost:11434", "nomic-embed-text", 768, "gemma4-e4b").expect("failed to construct ollama client"));
             if let Err(err) = pipeline::start_scheduler(db, llm).await {
                 tracing::error!(?err, "failed to start background job scheduler");
             }