[{"data":1,"prerenderedAt":107},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-fr-ollama":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"name":8,"description":9,"phase":10,"docsUrl":11,"logo":12,"github":13,"tagline":14,"longDescription":15,"features":16,"useCases":23,"steps":33,"faq":49,"specs":68,"compatibleOs":76,"relatedApps":78,"relatedPosts":101,"category":104},"ollama","Ollama","Run open-source LLMs locally via a dead-simple API. Pull Llama 3, Mistral, Qwen or DeepSeek in one command — OpenAI-compatible, zero per-token cost.",1,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-ollama-vps","https:\u002F\u002Fcdn.simpleicons.org\u002Follama","https:\u002F\u002Fgithub.com\u002Follama\u002Follama","Run open-source LLMs on your VPS — OpenAI-compatible API, zero per-token cost.","Ollama is an open-source LLM runtime that lets you pull and serve large language models (Llama 3, Mistral, Qwen, DeepSeek, Gemma) on your own infrastructure with a single command. It exposes an OpenAI-compatible REST API on port 11434, so any tool or library that works with OpenAI also works with your self-hosted instance — without changing a single line of code.\n\nDeployed on a ServOrbit VPS, Ollama becomes your private AI inference backend: unlimited requests at a fixed monthly cost, with all prompts and responses staying on your server. It pairs directly with Open WebUI for a chat interface, Flowise or n8n for automation, or any custom application that calls `\u002Fv1\u002Fchat\u002Fcompletions`.",[17,18,19,20,21,22],"OpenAI-compatible API — swap the base URL and your existing code works instantly","One-command model management: `ollama pull llama3.1:8b`, `ollama list`, `ollama rm`","Supports Llama 3, Mistral, Qwen, DeepSeek, Gemma, Phi and 100+ other models","CPU-only mode works out of the box; optional GPU passthrough for faster inference","Multi-model server: load several models concurrently, each on its own port or context","Persistent model storage in a Docker volume — models survive container restarts",[24,27,30],{"title":25,"body":26},"Private AI backend","Replace OpenAI API calls with your own Ollama endpoint. Your prompts never leave your VPS — ideal for processing contracts, internal documents, or any sensitive data.",{"title":28,"body":29},"Local dev & testing","Run a 7B or 13B model on a dedicated VPS to prototype AI features before wiring up a production LLM. Fixed cost, no surprise bills, reset with `ollama rm`.",{"title":31,"body":32},"Shared team AI stack","Pair Ollama with Open WebUI to give your whole team a shared ChatGPT-like interface powered by open-source models — on infrastructure you control.",[34,37,40,43,46],{"title":35,"body":36},"Create the VPS","Order a ServOrbit VPS with at least 8 GB RAM (for a 7B\u002F8B Q4 model in CPU mode) or 16 GB for larger models. Ubuntu 22.04 is recommended. For production-grade latency, a VPS with a GPU changes the experience significantly.",{"title":38,"body":39},"Deploy Ollama","Connect via SSH and run: `docker run -d -v ollama:\u002Froot\u002F.ollama -p 127.0.0.1:11434:11434 --name ollama --restart always ollama\u002Follama`. Binding to `127.0.0.1` keeps the API off the public internet — it will sit behind your reverse proxy.",{"title":41,"body":42},"Pull your first model","Download a model: `docker exec -it ollama ollama pull llama3.1:8b`. Check it's running: `docker exec -it ollama ollama list`. Test locally: `curl http:\u002F\u002F127.0.0.1:11434\u002Fapi\u002Fgenerate -d '{\"model\":\"llama3.1:8b\",\"prompt\":\"Hello\"}'`.",{"title":44,"body":45},"Add a reverse proxy with auth","Ollama has no built-in authentication. Use Caddy or Nginx to terminate TLS and add a Bearer-token layer before exposing the API externally. Example Caddyfile: `reverse_proxy localhost:11434 { header_up Authorization \"Bearer {env.OLLAMA_TOKEN}\" }`.",{"title":47,"body":48},"Connect your tools","In Open WebUI → Settings → Connections, set the Ollama URL to `http:\u002F\u002Flocalhost:11434`. In any OpenAI SDK, set `base_url='http:\u002F\u002F\u003Cyour-vps-ip>:11434\u002Fv1'` and `api_key='ollama'`. Your tools now use your models.",[50,53,56,59,62,65],{"q":51,"a":52},"What is Ollama?","Ollama is an open-source runtime that downloads and serves large language models (LLMs) via a local REST API. Think of it as a local inference server: you pull a model once, and any application can call it just like it would call the OpenAI API.",{"q":54,"a":55},"How much RAM does Ollama need?","A 7B parameter model in Q4 quantization requires roughly 5–6 GB of RAM. Plan for 8 GB minimum to run a 7B\u002F8B model comfortably. For 13B models, 16 GB; for 70B models (slow on CPU), 64 GB or a GPU is recommended.",{"q":57,"a":58},"Is Ollama compatible with the OpenAI SDK?","Yes. Ollama exposes an OpenAI-compatible endpoint at `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fv1\u002Fcompletions`, and `\u002Fv1\u002Fembeddings`. Change `base_url` to your Ollama host and set `api_key` to any non-empty string — existing code requires no other changes.",{"q":60,"a":61},"Does Ollama work without a GPU?","Yes. CPU-only inference works out of the box. Smaller quantized models (Q4_K_M) run at usable speeds on modern CPUs for dev or low-volume use. For production latency on 7B+ models, a GPU accelerates inference 10–30×.",{"q":63,"a":64},"How do I add more models?","Run `docker exec -it ollama ollama pull \u003Cmodel-name>` from your VPS. Browse available models at ollama.com\u002Flibrary. Popular choices: `llama3.1:8b`, `mistral:7b`, `qwen2.5:7b`, `deepseek-r1:7b`, `gemma2:9b`.",{"q":66,"a":67},"Can I pair Ollama with Open WebUI?","Yes — they are designed to work together. Open WebUI auto-detects a local Ollama instance and lists all pulled models in its model selector. Both can run on the same VPS; Open WebUI adds a full chat UI, user management, and RAG on top of Ollama's inference engine.",{"ram":69,"cpu":70,"stack":71,"port":75},"8 Go minimum (16 Go recommandé)","2 vCPU",[72,73,74],"Docker","Go","llama.cpp","11434",[77],"ubuntu-24.04",[79,88,96],{"name":80,"slug":81,"categorySlug":82,"categoryName":83,"categoryColor":84,"logo":85,"tagline":86,"description":87},"Open WebUI","open-webui","ia","Intelligence Artificielle","text-purple-400 bg-purple-500\u002F10",null,"Interface web pour vos LLMs — Ollama, OpenAI, Mistral — hébergée sur votre propre serveur.","Interface web pour interagir avec vos LLMs locaux ou distants. Vos données restent sur votre infrastructure — aucun tiers impliqué.",{"name":89,"slug":90,"categorySlug":91,"categoryName":92,"categoryColor":93,"logo":85,"tagline":94,"description":95},"Flowise","flowise","automatisation","Automatisation & Workflows","text-brand-action bg-brand-action\u002F10","Construisez des pipelines LLM et des chatbots IA en drag-and-drop — LangChain visuel.","Construisez des pipelines d'automatisation LLM en drag-and-drop. Chaînes LangChain visuelles, connectées à vos outils existants.",{"name":97,"slug":97,"categorySlug":91,"categoryName":92,"categoryColor":93,"logo":98,"tagline":99,"description":100},"n8n","https:\u002F\u002Fcdn.simpleicons.org\u002Fn8n","Automatisez vos processus métier avec 400+ intégrations — 100 % auto-hébergé sur votre VPS.","Automatisez vos workflows entre applications sans code. Plus de 400 intégrations, 100 % auto-hébergé sur votre VPS.",[102,103],"heberger-ollama-vps","ollama-vs-localai",{"key":82,"slug":82,"name":83,"objective":105,"icon":106,"color":84},"Créer, héberger et exploiter des solutions IA.","ai",1784126253549]