{"id":490,"date":"2026-09-23T13:00:00","date_gmt":"2026-09-23T11:00:00","guid":{"rendered":"https:\/\/www.lukaswojcik.com\/?p=490"},"modified":"2026-09-10T10:52:42","modified_gmt":"2026-09-10T08:52:42","slug":"self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy","status":"publish","type":"post","link":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/","title":{"rendered":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy"},"content":{"rendered":"\r\n<p class=\"wp-block-paragraph\">Das \u00dcbertragen vertraulicher Unternehmensdokumente, Kundendaten und Quellcodes an \u00f6ffentliche Large-Language-Model-APIs (LLM) wie OpenAI, Anthropic oder Google Gemini birgt gravierende Datenschutzrisiken und potenzielle DSGVO-Verst\u00f6\u00dfe. Das Hosting offener KI-Modelle \u2013 wie Llama 3.1, Mistral oder CodeLlama \u2013 auf firmeneigener Server-Hardware garantiert absolute Datenhoheit. Da der popul\u00e4re Inferenzserver Ollama seine REST-API standardm\u00e4\u00dfig auf Port <code>11434<\/code> v\u00f6llig ohne native Authentifizierung bereitstellt, erfordert der sichere Betrieb im Unternehmensnetzwerk eine gesch\u00fctzte Architektur: einen Nginx-Reverse-Proxy zur Durchsetzung strenger API-Token-Authentifizierung und TLS-Verschl\u00fcsselung.<\/p>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\">1. Architektur-Grundlagen: Sichere Edge-Inferenz-Pipeline<\/h2>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\">Ein professionelles, lokales LLM-Deployment entkoppelt die Modellausf\u00fchrung von der Netzwerkfreigabe durch die Schichtung dreier isolierter Dienste innerhalb einer Container-Umgebung:<\/p>\r\n\r\n\r\n\r\n<ul class=\"wp-block-list\">\r\n<li><strong>Ollama-Inferenz-Backend:<\/strong> F\u00fchrt offene LLM-Gewichte unter Nutzung von NVIDIA-GPU-Beschleunigung (via NVIDIA Container Toolkit) oder CPU-Quantisierung aus und ist ausschlie\u00dflich an interne Container-Netzwerkschnittstellen gebunden.<\/li>\r\n<li><strong>Nginx-Authentifizierungs- &amp; TLS-Proxy:<\/strong> Agiert als zentraler Einlasspunkt, abf\u00e4ngt s\u00e4mtliche HTTP-Anfragen, terminiert SSL\/TLS-Zertifikate und validiert Bearer-Token oder HTTP-Basic-Auth-Zugangsdaten, bevor Anfragen an Ollama weitergeleitet werden.<\/li>\r\n<li><strong>OpenAI-kompatibles Frontend \/ Skripte:<\/strong> Interne Web-Oberfl\u00e4chen (wie Open WebUI) oder automatisierte Python-Skripte kommunizieren \u00fcber standardisierte OpenAI-SDK-Syntaxen mit dem abgesicherten Endpunkt, ohne den Sicherheits-Proxy zu umgehen.<\/li>\r\n<\/ul>\r\n\r\n\r\n\r\n<figure class=\"lw-diagram\">\n<img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/diagrams\/hand-ollama-de.png\" width=\"1120\" height=\"580\" alt=\"Perimeter-Diagramm: Nur Port 8443 des nginx-Auth-Proxys ist ver\u00f6ffentlicht, das Ollama-Backend auf 11434 bleibt im Docker-Bridge-Netz\">\n<figcaption>Das Inferenz-Backend ber\u00fchrt die Au\u00dfenwelt nie. Ver\u00f6ffentlicht ist allein der Proxy, und der antwortet ohne Anmeldung gar nicht \u2014 das erst macht aus einem lokalen Modell einen internen Dienst.<\/figcaption>\n<\/figure>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\">2. Schritt-f\u00fcr-Schritt-Container- &amp; GPU-Bereitstellung<\/h2>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\">Um Ollama zusammen mit einem dedizierten Nginx-Reverse-Proxy zu betreiben, wird die folgende produktionsreife <code>docker-compose.yml<\/code> f\u00fcr GPU-Passthrough und isoliertes Networking bereitgestellt:<\/p>\r\n\r\n\r\n\r\n<pre class=\"wp-block-code\"><code class=\"language-yaml\">services:\n  ollama:\n    image: ollama\/ollama:latest\n    container_name: enterprise_ollama\n    restart: always\n    environment:\n      - OLLAMA_HOST=0.0.0.0\n      - OLLAMA_ORIGINS=*\n    volumes:\n      - .\/ollama_data:\/root\/.ollama\n    deploy:\n      resources:\n        reservations:\n          devices:\n            - driver: nvidia\n              count: all\n              capabilities: [gpu]\n    networks:\n      - llm_internal\n\n  auth_proxy:\n    image: nginx:alpine\n    container_name: ollama_auth_proxy\n    restart: always\n    ports:\n      - \"8443:443\"\n    volumes:\n      - .\/nginx.conf:\/etc\/nginx\/nginx.conf:ro\n      - .\/certs:\/etc\/nginx\/certs:ro\n      - .\/htpasswd:\/etc\/nginx\/.htpasswd:ro\n    depends_on:\n      - ollama\n    networks:\n      - llm_internal\n\nnetworks:\n  llm_internal:\n    driver: bridge<\/code><\/pre>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\">3. Schritt-f\u00fcr-Schritt-Konfiguration des Nginx-Auth-Proxys<\/h2>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\">Um den API-Zugriff ausschlie\u00dflich auf autorisierte Unternehmensanwendungen zu beschr\u00e4nken, wird Nginx mit HTTP Basic Authentication oder API-Token-Abfragen konfiguriert. Das folgende <code>nginx.conf<\/code>-Skript erzwingt die Authentifizierung und verl\u00e4ngert Timeouts f\u00fcr langandauernde Streaming-Inferenz-Antworten:<\/p>\r\n\r\n\r\n\r\n<pre class=\"wp-block-code\"><code class=\"language-nginx\">events {\n    worker_connections 1024;\n}\n\nhttp {\n    upstream ollama_backend {\n        server ollama:11434;\n    }\n\n    server {\n        listen 443 ssl;\n        server_name llm.internal.domain;\n\n        ssl_certificate \/etc\/nginx\/certs\/server.crt;\n        ssl_certificate_key \/etc\/nginx\/certs\/server.key;\n        ssl_protocols TLSv1.2 TLSv1.3;\n\n        # Erzwingung von HTTP Basic Auth (Erstellung via: htpasswd -c .\/htpasswd api_user)\n        auth_basic \"Enterprise LLM Secure Gateway\";\n        auth_basic_user_file \/etc\/nginx\/.htpasswd;\n\n        # Obligatorische Timeout-Erweiterungen f\u00fcr langes Inferenz-Streaming\n        proxy_read_timeout 600s;\n        proxy_connect_timeout 600s;\n        proxy_send_timeout 600s;\n\n        location \/ {\n            proxy_pass http:\/\/ollama_backend;\n            proxy_set_header Host $host;\n            proxy_set_header X-Real-IP $remote_addr;\n            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;\n            proxy_set_header X-Forwarded-Proto $scheme;\n            \n            # Streaming-Unterst\u00fctzung f\u00fcr Server-Sent Events (SSE)\n            proxy_buffering off;\n            proxy_cache off;\n        }\n    }\n}<\/code><\/pre>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\">4. Schritt-f\u00fcr-Schritt-Verifizierung mit Skripten &amp; Web UI<\/h2>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\">Sobald der Proxy aktiv ist, l\u00e4sst sich die Inferenz-Engine sicher \u00fcber Skripte abfragen oder in Chat-Oberfl\u00e4chen anbinden:<\/p>\r\n\r\n\r\n\r\n<ol class=\"wp-block-list\">\r\n<li><strong>Modell-Download:<\/strong> Der initiale Modell-Download erfolgt direkt im Container \u00fcber das CLI:\r\n    <br><code>docker exec -it enterprise_ollama ollama run llama3.1<\/code>\r\n<\/li>\r\n<li><strong>Python-API-Verifizierung:<\/strong> Versand einer authentifizierten HTTPS-REST-Anfrage an den Proxy unter Angabe der Basic-Auth-Zugangsdaten:\r\n    <br><code>curl -k -u \"api_user:SecretPassword123\" https:\/\/localhost:8443\/api\/generate -d '{\"model\": \"llama3.1\", \"prompt\": \"Zusammenfassung der Datenschutzrichtlinie.\", \"stream\": false}'<\/code>\r\n<\/li>\r\n<li><strong>Anbindung an Open WebUI:<\/strong> Bereitstellung des <code>open-webui<\/code>-Docker-Containers im selben Netzwerk unter Konfiguration der Endpunkt-Umgebungsvariable:\r\n    <br><code>OLLAMA_BASE_URL=https:\/\/api_user:SecretPassword123@auth_proxy:443<\/code>\r\n<\/li>\r\n<\/ol>\r\n\r\n\r\n\r\n<h2 class=\"wp-block-heading\">5. Zusammenfassung &amp; Mehrwert<\/h2>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\"><strong>Was sich damit erreichen l\u00e4sst:<\/strong> Die erfolgreiche Bereitstellung eines selbstgehosteten, GPU-beschleunigten Inferenz-Servers f\u00fcr offene LLMs mit Ollama, abgesichert durch einen Nginx-Authentifizierungs- und SSL\/TLS-Reverse-Proxy.<\/p>\r\n\r\n\r\n\r\n<p class=\"wp-block-paragraph\"><strong>Resultierender Mehrwert:<\/strong> Ein privates, leistungsstarkes \u201eChatGPT\u201c-\u00c4quivalent steht f\u00fcr interne Unternehmensabl\u00e4ufe, Software-Skripte und Mitarbeiter-Benutzeroberfl\u00e4chen zur Verf\u00fcgung, ohne dass sensible Daten an externe KI-Anbieter abflie\u00dfen. Die absolute Datenhoheit und vollst\u00e4ndige DSGVO-Konformit\u00e4t sind gew\u00e4hrleistet, w\u00e4hrend obligatorische Authentifizierungsmechanismen unbefugte Zugriffe auf die Rechenressourcen verhindern.<\/p>\r\n\n\n<div class=\"lw-quellen\">\n<h2>Quellen<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/ollama\/ollama\/blob\/main\/README.md\" target=\"_blank\" rel=\"noopener noreferrer\">Ollama documentation<\/a><\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Eine technische Anleitung zur Bereitstellung eines privaten, GPU-beschleunigten LLM-Servers mit Ollama hinter einem sicheren Nginx-Authentifizierungs-Proxy.<\/p>\n","protected":false},"author":1,"featured_media":14050,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[92638],"tags":[92406,92205,92337,92418,92211,92340,92235,92071],"class_list":["post-490","post","type-post","status-publish","format-standard","hentry","category-tutorials-de-cloud-ai-de","tag-artificial-intelligence-de","tag-homelab-de","tag-linux-de","tag-llm-de","tag-self-hosting-de","tag-server-administration-de","tag-tutorial-de","tag-web-security-de"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog\" \/>\n<meta property=\"og:description\" content=\"Eine technische Anleitung zur Bereitstellung eines privaten, GPU-beschleunigten LLM-Servers mit Ollama hinter einem sicheren Nginx-Authentifizierungs-Proxy.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/\" \/>\n<meta property=\"og:site_name\" content=\"Lukas Wojcik - Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-23T11:00:00+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"630\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Lukas Wojcik\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Lukas Wojcik\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/\"},\"author\":{\"name\":\"Lukas Wojcik\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#\\\/schema\\\/person\\\/895f7604f9b6b71aad9bba33af28d0f9\"},\"headline\":\"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy\",\"datePublished\":\"2026-09-23T11:00:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/\"},\"wordCount\":423,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#\\\/schema\\\/person\\\/895f7604f9b6b71aad9bba33af28d0f9\"},\"image\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/hero-490-self-hosted-large-language-model-llm-g.png\",\"keywords\":[\"Artificial Intelligence\",\"Homelab\",\"Linux\",\"LLM\",\"Self-Hosting\",\"Server Administration\",\"Tutorial\",\"Web Security\"],\"articleSection\":[\"Tutorials\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/\",\"url\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/\",\"name\":\"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/hero-490-self-hosted-large-language-model-llm-g.png\",\"datePublished\":\"2026-09-23T11:00:00+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/hero-490-self-hosted-large-language-model-llm-g.png\",\"contentUrl\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/hero-490-self-hosted-large-language-model-llm-g.png\",\"width\":1200,\"height\":630,\"caption\":\"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/de\\\/cloud-ai-de\\\/tutorials-de-cloud-ai-de\\\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/\",\"name\":\"Lukas Wojcik - Blog\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#\\\/schema\\\/person\\\/895f7604f9b6b71aad9bba33af28d0f9\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/#\\\/schema\\\/person\\\/895f7604f9b6b71aad9bba33af28d0f9\",\"name\":\"Lukas Wojcik\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/lw-x2.jpg\",\"url\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/lw-x2.jpg\",\"contentUrl\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/lw-x2.jpg\",\"width\":424,\"height\":636,\"caption\":\"Lukas Wojcik\"},\"logo\":{\"@id\":\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/lw-x2.jpg\"},\"sameAs\":[\"https:\\\/\\\/www.lukaswojcik.com\\\/blog\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/","og_locale":"en_US","og_type":"article","og_title":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog","og_description":"Eine technische Anleitung zur Bereitstellung eines privaten, GPU-beschleunigten LLM-Servers mit Ollama hinter einem sicheren Nginx-Authentifizierungs-Proxy.","og_url":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/","og_site_name":"Lukas Wojcik - Blog","article_published_time":"2026-09-23T11:00:00+00:00","og_image":[{"width":1200,"height":630,"url":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png","type":"image\/png"}],"author":"Lukas Wojcik","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Lukas Wojcik","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#article","isPartOf":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/"},"author":{"name":"Lukas Wojcik","@id":"https:\/\/www.lukaswojcik.com\/blog\/#\/schema\/person\/895f7604f9b6b71aad9bba33af28d0f9"},"headline":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy","datePublished":"2026-09-23T11:00:00+00:00","mainEntityOfPage":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/"},"wordCount":423,"commentCount":0,"publisher":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/#\/schema\/person\/895f7604f9b6b71aad9bba33af28d0f9"},"image":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#primaryimage"},"thumbnailUrl":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png","keywords":["Artificial Intelligence","Homelab","Linux","LLM","Self-Hosting","Server Administration","Tutorial","Web Security"],"articleSection":["Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/","url":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/","name":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy - Lukas Wojcik - Blog","isPartOf":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#primaryimage"},"image":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#primaryimage"},"thumbnailUrl":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png","datePublished":"2026-09-23T11:00:00+00:00","breadcrumb":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#primaryimage","url":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png","contentUrl":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/09\/hero-490-self-hosted-large-language-model-llm-g.png","width":1200,"height":630,"caption":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy"},{"@type":"BreadcrumbList","@id":"https:\/\/www.lukaswojcik.com\/blog\/de\/cloud-ai-de\/tutorials-de-cloud-ai-de\/self-hosted-large-language-model-llm-mit-ollama-hinter-einem-auth-proxy\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.lukaswojcik.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Self-Hosted Large Language Model (LLM) mit Ollama hinter einem Auth-Proxy"}]},{"@type":"WebSite","@id":"https:\/\/www.lukaswojcik.com\/blog\/#website","url":"https:\/\/www.lukaswojcik.com\/blog\/","name":"Lukas Wojcik - Blog","description":"","publisher":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/#\/schema\/person\/895f7604f9b6b71aad9bba33af28d0f9"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.lukaswojcik.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/www.lukaswojcik.com\/blog\/#\/schema\/person\/895f7604f9b6b71aad9bba33af28d0f9","name":"Lukas Wojcik","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/07\/lw-x2.jpg","url":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/07\/lw-x2.jpg","contentUrl":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/07\/lw-x2.jpg","width":424,"height":636,"caption":"Lukas Wojcik"},"logo":{"@id":"https:\/\/www.lukaswojcik.com\/blog\/wp-content\/uploads\/2026\/07\/lw-x2.jpg"},"sameAs":["https:\/\/www.lukaswojcik.com\/blog"]}]}},"_links":{"self":[{"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/posts\/490","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/comments?post=490"}],"version-history":[{"count":5,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/posts\/490\/revisions"}],"predecessor-version":[{"id":17956,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/posts\/490\/revisions\/17956"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/media\/14050"}],"wp:attachment":[{"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/media?parent=490"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/categories?post=490"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lukaswojcik.com\/blog\/wp-json\/wp\/v2\/tags?post=490"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}