<titledata-rh="true">Starting an inference server | Podman Desktop</title><metadata-rh="true"name="viewport"content="width=device-width,initial-scale=1"><metadata-rh="true"name="twitter:card"content="summary_large_image"><metadata-rh="true"property="og:image"content="https://podman-desktop.io/img/banner_podman-desktop.png"><metadata-rh="true"name="twitter:image"content="https://podman-desktop.io/img/banner_podman-desktop.png"><metadata-rh="true"property="og:url"content="https://podman-desktop.io/docs/ai-lab/start-inference-server"><metadata-rh="true"property="og:locale"content="en"><metadata-rh="true"name="docusaurus_locale"content="en"><metadata-rh="true"name="docsearch:language"content="en"><metadata-rh="true"name="docusaurus_version"content="current"><metadata-rh="true"name="docusaurus_tag"content="docs-default-current"><metadata-rh="true"name="docsearch:version"content="current"><metadata-rh="true"name="docsearch:docusaurus_tag"content="docs-default-current"><metadata-rh="true"property="og:title"content="Starting an inference server | Podman Desktop"><metadata-rh="true"name="description"content="Starting an inference server for a model."><metadata-rh="true"property="og:description"content="Starting an inference server for a model."><metadata-rh="true"name="keywords"content="podman desktop,podman,ai,llm,generative ai"><linkdata-rh="true"rel="icon"href="/img/favicon.ico"><linkdata-rh="true"rel="canonical"href="https://podman-desktop.io/docs/ai-lab/start-inference-server"><linkdata-rh="true"rel="alternate"href="https://podman-desktop.io/docs/ai-lab/start-inference-server"hreflang="en"><linkdata-rh="true"rel="alternate"href="https://podman-desktop.io/docs/ai-lab/start-inference-server"hreflang="x-default"><linkdata-rh="true"rel="preconnect"href="https://MR01ANKQ9S-dsn.algolia.net"crossorigin="anonymous"><linkrel="alternate"type="application/rss+xml"href="/blog/rss.xml"title="Podman Desktop RSS Feed">
<linkrel="alternate"type="application/atom+xml"href="/blog/atom.xml"title="Podman Desktop Atom Feed">
<p>Once a model is downloaded, a model service can be started. A model service is an inference server that is running in a container and exposing the model through the well-known chat API common to many providers.</p>
<h4class="anchor anchorWithStickyNavbar_JmGV"id="prerequisites">Prerequisites<ahref="#prerequisites"class="hash-link"aria-label="Direct link to Prerequisites"title="Direct link to Prerequisites"></a></h4>
<h4class="anchor anchorWithStickyNavbar_JmGV"id="procedure">Procedure<ahref="#procedure"class="hash-link"aria-label="Direct link to Procedure"title="Direct link to Procedure"></a></h4>
<li>Click the Podman AI Lab icon in the navigation bar</li>
<li>In the Podman AI Lab navigation bar, click <strong>Models > Services</strong> menu item.</li>
<li>Click the <strong>New Model Service</strong> button on the top right.</li>
<li>Select the model you want to start an inference server for in the <strong>Model</strong> list and click the <strong>Create Service</strong> button.</li>
<li>The inference server for the model is being started and after a while, click on the <strong>Open service details</strong> button.</li>
<h4class="anchor anchorWithStickyNavbar_JmGV"id="verification">Verification<ahref="#verification"class="hash-link"aria-label="Direct link to Verification"title="Direct link to Verification"></a></h4>
<li>Once the inference server is started, the details for the inference server allows you to generate code snippets in various languages to access the model through the inference server.