diff --git a/Cargo.lock b/Cargo.lock
index 4cbc4da..849e952 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -253,6 +253,7 @@ name = "doubleo7"
 version = "0.1.0"
 dependencies = [
  "anyhow",
+ "reqwest 0.12.28",
  "rig-core",
  "serde",
  "tokio",
@@ -325,6 +326,21 @@ version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
+[[package]]
+name = "foreign-types"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6f339eb8adc052cd2ca78910fda869aefa38d22d5cb648e6485e4d3fc06f3b1"
+dependencies = [
+ "foreign-types-shared",
+]
+
+[[package]]
+name = "foreign-types-shared"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "00b0228411908ca8685dba7fc2cdd70ec9990a6e753e89b6ac91a84c40fbaf4b"
+
 [[package]]
 name = "form_urlencoded"
 version = "1.2.2"
@@ -605,6 +621,22 @@ dependencies = [
  "tower-service",
 ]
 
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
 [[package]]
 name = "hyper-util"
 version = "0.1.20"
@@ -831,6 +863,12 @@ version = "0.2.189"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2"
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
+
 [[package]]
 name = "litemap"
 version = "0.8.2"
@@ -897,6 +935,23 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "native-tls"
+version = "0.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "465500e14ea162429d264d44189adc38b199b62b1c21eea9f69e4b73cb03bbf2"
+dependencies = [
+ "libc",
+ "log",
+ "openssl",
+ "openssl-probe",
+ "openssl-sys",
+ "schannel",
+ "security-framework",
+ "security-framework-sys",
+ "tempfile",
+]
+
 [[package]]
 name = "nom"
 version = "7.1.3"
@@ -922,12 +977,49 @@ version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
+[[package]]
+name = "openssl"
+version = "0.10.81"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77823a27f0babb03091cb9ed9ef80af3b39dbc82f97e8fa530374b7dafd87a45"
+dependencies = [
+ "bitflags",
+ "cfg-if",
+ "foreign-types",
+ "libc",
+ "openssl-macros",
+ "openssl-sys",
+]
+
+[[package]]
+name = "openssl-macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
 [[package]]
 name = "openssl-probe"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
 
+[[package]]
+name = "openssl-sys"
+version = "0.9.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b47e7e6bb2c38cd930d25a23b40fa52e068c10e85f3e03a7f5ba5aaca5713695"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
 [[package]]
 name = "ordered-float"
 version = "5.3.0"
@@ -1196,6 +1288,46 @@ dependencies = [
  "syn 3.0.3",
 ]
 
+[[package]]
+name = "reqwest"
+version = "0.12.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
+dependencies = [
+ "base64",
+ "bytes",
+ "encoding_rs",
+ "futures-core",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-tls",
+ "hyper-util",
+ "js-sys",
+ "log",
+ "mime",
+ "native-tls",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tokio-native-tls",
+ "tower",
+ "tower-http",
+ "tower-service",
+ "url",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
 [[package]]
 name = "reqwest"
 version = "0.13.4"
@@ -1260,7 +1392,7 @@ dependencies = [
  "mime_guess",
  "ordered-float",
  "pin-project-lite",
- "reqwest",
+ "reqwest 0.13.4",
  "rig-derive",
  "schemars",
  "serde",
@@ -1314,6 +1446,19 @@ dependencies = [
  "semver",
 ]
 
+[[package]]
+name = "rustix"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "rustls"
 version = "0.23.43"
@@ -1395,6 +1540,12 @@ version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f"
 
+[[package]]
+name = "ryu"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
+
 [[package]]
 name = "same-file"
 version = "1.0.6"
@@ -1542,6 +1693,18 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "serde_urlencoded"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd"
+dependencies = [
+ "form_urlencoded",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
 [[package]]
 name = "sha1"
 version = "0.10.7"
@@ -1682,6 +1845,19 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "tempfile"
+version = "3.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
+dependencies = [
+ "fastrand",
+ "getrandom 0.4.3",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.19"
@@ -1755,6 +1931,16 @@ dependencies = [
  "syn 3.0.3",
 ]
 
+[[package]]
+name = "tokio-native-tls"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2"
+dependencies = [
+ "native-tls",
+ "tokio",
+]
+
 [[package]]
 name = "tokio-rustls"
 version = "0.26.4"
@@ -2013,6 +2199,12 @@ version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
 
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
 [[package]]
 name = "version_check"
 version = "0.9.5"
diff --git a/Cargo.toml b/Cargo.toml
index a00633b..44059af 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -5,6 +5,7 @@ edition = "2024"
 
 [dependencies]
 anyhow = "1.0.104"
+reqwest = "0.12"
 rig-core = { git = "https://github.com/0xPlaygrounds/rig", branch = "main" }
 serde = "1.0.229"
 tokio = { version = "1.53.1", features = ["full"] }
diff --git a/src/main.rs b/src/main.rs
index 36e863e..fe5af3e 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -13,8 +13,7 @@ use rig_core::serde_json::json;
 use crate::models::Prompts;
 
 mod models;
-
-const LLAMA_SERVER_URL: &str = "http://127.0.0.1:8000";
+mod server;
 
 static PROMPTS: LazyLock<Prompts> = LazyLock::new(|| {
     toml::from_str(include_str!("prompts.toml")).expect("Could not parse prompts.toml")
@@ -22,7 +21,9 @@ static PROMPTS: LazyLock<Prompts> = LazyLock::new(|| {
 
 #[tokio::main]
 async fn main() -> anyhow::Result<()> {
-    let gemma: ollama::CompletionModel = wire_gemma_client().await?;
+    // Independent setup steps (talk to unrelated backends, no data dependency) — run concurrently.
+    let (gemma, ()) = tokio::try_join!(wire_gemma_client(), server::ensure_running())?;
+
     let shieldstral = wire_shieldstral().await?;
 
     let prompt_to_test = gemma.completion_request(&PROMPTS.gemma.prompt)
@@ -53,7 +54,7 @@ async fn wire_gemma_client() -> anyhow::Result<ollama::CompletionModel> {
 }
 
 async fn wire_shieldstral() -> anyhow::Result<GenericCompletionModel<LlamafileExt>> {
-    let client = llamafile::Client::from_url(LLAMA_SERVER_URL)?;
+    let client = llamafile::Client::from_url(&server::url())?;
 
     // Name doesn't matter here, server just uses whatever is running on it.
     let shieldstral = client.completion_model("shieldstral");
diff --git a/src/server.rs b/src/server.rs
new file mode 100644
index 0000000..f3f197d
--- /dev/null
+++ b/src/server.rs
@@ -0,0 +1,68 @@
+use std::sync::LazyLock;
+use std::time::Duration;
+use serde::Deserialize;
+use tokio::process::Command;
+use tokio::time::sleep;
+
+#[derive(Deserialize)]
+struct ServerConfig {
+    llama_server: LlamaServerConfig,
+}
+
+#[derive(Deserialize)]
+struct LlamaServerConfig {
+    binary: String,
+    model_path: String,
+    host: String,
+    port: u16,
+    context_size: u32,
+}
+
+static SERVER_CONFIG: LazyLock<ServerConfig> = LazyLock::new(|| {
+    toml::from_str(include_str!("server.toml")).expect("Could not parse server.toml")
+});
+
+static HTTP_CLIENT: LazyLock<reqwest::Client> = LazyLock::new(reqwest::Client::new);
+
+pub(crate) fn url() -> String {
+    format!("http://{}:{}", SERVER_CONFIG.llama_server.host, SERVER_CONFIG.llama_server.port)
+}
+
+async fn is_healthy(health_url: &str) -> bool {
+    HTTP_CLIENT.get(health_url).send().await.is_ok_and(|r| r.status().is_success())
+}
+
+/// Checks whether llama-server is already serving on the configured host/port,
+/// and if not, spawns it from the configured binary/model path and waits for
+/// it to report healthy before returning.
+pub(crate) async fn ensure_running() -> anyhow::Result<()> {
+    let base_url = url();
+    let health_url = format!("{base_url}/health");
+
+    if is_healthy(&health_url).await {
+        return Ok(());
+    }
+
+    println!("llama-server not running at {base_url}, starting it...");
+
+    Command::new(&SERVER_CONFIG.llama_server.binary)
+        .args([
+            "-m", &SERVER_CONFIG.llama_server.model_path,
+            "--jinja",
+            "-c", &SERVER_CONFIG.llama_server.context_size.to_string(),
+            "--host", &SERVER_CONFIG.llama_server.host,
+            "--port", &SERVER_CONFIG.llama_server.port.to_string(),
+        ])
+        .spawn()
+        .map_err(|e| anyhow::anyhow!("failed to spawn llama-server at {}: {e}", SERVER_CONFIG.llama_server.binary))?;
+
+    for _ in 0..60 {
+        if is_healthy(&health_url).await {
+            println!("llama-server is up.");
+            return Ok(());
+        }
+        sleep(Duration::from_secs(1)).await;
+    }
+
+    anyhow::bail!("llama-server did not become healthy within 60s")
+}
diff --git a/src/server.toml b/src/server.toml
new file mode 100644
index 0000000..97bf814
--- /dev/null
+++ b/src/server.toml
@@ -0,0 +1,6 @@
+[llama_server]
+binary = "/home/austin/.local/share/llama.cpp/build/bin/llama-server"
+model_path = "/home/austin/ai/Shieldstral-1.0-3B-BF16.gguf"
+host = "127.0.0.1"
+port = 8000
+context_size = 32768