> Markdown twin of https://conduitllm.com/use-cases/local-llm.html > A desktop chat app for the model you run in Ollama, LM Studio, or vLLM. No key, no bill — documents, tools, and artifacts work as they do with a cloud model. --- 1. [Conduit](https://conduitllm.com/) 2. [Use cases](https://conduitllm.com/use-cases.html) 3. Local models For local-model users # Local models, with *a real app* around them Conduit doesn't run, download, or manage models — it's a desktop app that connects to the local server you already have running: Ollama or LM Studio directly, or any OpenAI-compatible endpoint such as a self-hosted vLLM or SGLang server. No key, no bill, and the rest of the app — documents, MCP tools, artifacts, skills, memory — works exactly the same as it does with a cloud model. [Download Conduit](https://conduitllm.com/#get) See which runtime fits - No key, no bill for local models - Can run with no internet at all - Ollama, LM Studio, or any OpenAI-compatible endpoint Your server runs the model; Conduit is the app around it. With local-only mode on, web search and cloud document indexing are switched off. The problem You already have a model running — pulled into Ollama, loaded in LM Studio, or served off your own vLLM box. What's missing isn't a model. It's everything around it: a place to search old conversations, attach a file, call a tool, or reach a cloud model without switching to a different window entirely. What you get ## The engine you already run, a real app around it Conduit doesn't touch your model files. It's the client, and your local server stays the thing doing inference. ### No key, no bill, nothing to fetch Conduit doesn't download or manage models — it connects to the server you already have running, so there's no credential to paste and no usage to meter. Local models price at $0 in the cost chart, because they cost you nothing. ### The whole app, not just a chat box Documents with Ollama embeddings, MCP tools, artifacts, skills, saved prompts, full-text search, apps, and workflows — all work the same whether the model behind them is on your machine or in the cloud. ### A cloud model, one keystroke away When a question needs a frontier model, switch providers without leaving the conversation. Stay on the local provider and that option is simply never used. [Every feature, with its limits](https://conduitllm.com/features.html) How it works ## Point Conduit at the server you already have Three steps. There's no model to pull through Conduit itself at any point. ### Start your local server Launch Ollama, LM Studio, or your own vLLM or SGLang server the way you already do, with whatever model you want loaded or pulled. ### Point Conduit at it In **Settings → Providers & Keys**, pick Ollama or LM Studio directly, or choose the OpenAI-compatible provider and paste your server's base URL. Neither local provider needs a key. ### Pick the model and start talking Choose it from the list Conduit fetches from your server. Documents, MCP tools, artifacts, and everything else in the app work exactly as they do with a hosted model. Pick your runtime ## Three ways in, one settings screen Exact screens, and any pre-filled defaults, are in [the documentation](https://conduitllm.com/docs.html#first-run) — this is what each one needs from you. | Runtime | What you paste | Credential | | --- | --- | --- | | Ollama | Its base URL — editable if you changed the port or run it elsewhere | None — local | | LM Studio | Its local server's base URL | None — local | | Any OpenAI-compatible server — vLLM, SGLang, a proxy such as LiteLLM | That endpoint's base URL | Optional, only if the endpoint requires one | All three are editable-base-URL providers, so pointing Conduit at a non-default port or another machine on your network is a settings change, not a rebuild. [Conduit vs Ollama's own app](https://conduitllm.com/compare/ollama.html) goes deeper on what a separate client adds on top of Ollama specifically. Limits ## What it does, and what it doesn't The full network breakdown, for every feature, lives on [the privacy page](https://conduitllm.com/privacy.html). ### What it does - Connects directly to Ollama, LM Studio, or any OpenAI-compatible server — vLLM, SGLang, a proxy — over its own API - Local-only mode switches off web search and cloud document indexing in one toggle - With a local provider and update checks left on manual, makes no internet request at all - Documents can be embedded fully on-device with Ollama, so with a local chat model a collection never leaves the machine - MCP tools, artifacts, skills, memory, and full-text search work the same as with a cloud model - A cloud provider is one keystroke away when you want one — the provider you select is the one that answers ### What it doesn't - Doesn't download, install, update, or manage models — that stays with Ollama, LM Studio, or your own server - Doesn't fake vision on a text-only model — an attached image is dropped with a stated reason instead - Doesn't generate images locally — image generation only runs on OpenAI, Gemini, or OpenRouter - Doesn't make a small model reason like a large one — speed and quality depend on your hardware and the model you loaded - Doesn't guarantee tool calling — that depends on whether the model you picked was trained to call tools at all - Doesn't ship code-signed installers yet — expect a SmartScreen or Gatekeeper prompt on first launch ## Local model questions **Does Conduit run models locally?** No — Conduit never runs, downloads, or manages model weights itself. It's a desktop chat app that connects to a local server you already have running — Ollama or LM Studio directly, or any OpenAI-compatible endpoint such as a self-hosted vLLM or SGLang box. Pulling, deleting, and upgrading models stays with that server, not with Conduit. **Is Conduit an Ollama GUI?** It's a client that sits on top of Ollama rather than a GUI built by the Ollama project itself. Ollama has to stay installed and running — Conduit calls its API to list the models you've pulled and stream chat against them, with no separate key or account needed. See [Conduit vs Ollama's own app](https://conduitllm.com/compare/ollama.html) for where each one is the better daily driver. **Can I use Conduit with LM Studio?** Yes. Pick LM Studio from the provider list in Settings, the same way as Ollama — no credential needed, and Conduit fetches whichever models it's serving. Point the base URL field at LM Studio's local server address if you're not using the default. **Does Conduit work with vLLM or SGLang?** Yes, through the OpenAI-compatible provider — the seventeenth provider Conduit ships, built for exactly this. Point it at your server's base URL and add a key only if your setup requires one; the same route covers any self-hosted proxy that speaks the OpenAI chat completions API. **Is local-only mode really offline?** With a local provider selected and update checks left on their default manual setting, yes — the model runs on your machine, and local-only mode additionally switches off web search and cloud document indexing, so nothing else in the app reaches out on its own. Turning on background update checks, or picking a cloud provider, is what changes that. **Can a local model use tools, see images, or generate pictures?** Tool use and vision depend on the model, not on Conduit — MCP and built-in tools work with any model whose adapter supports tool calls, and image attachments go to models that accept them; a text-only model such as DeepSeek gets an attached image dropped with a stated reason rather than a faked answer. Image generation itself only runs on OpenAI, Gemini, or OpenRouter today, never on a local model. Related ## Other ways people use Conduit For heavy AI users ### Pay per token, not per seat Your own API keys for every hosted provider, for the days a local model isn't quite enough. [Bring your own key](https://conduitllm.com/use-cases/bring-your-own-key.html) For developers ### An MCP client that asks first Local and remote servers, OAuth, and consent graded by what a tool can do — for a local model with something to do. Conduit as your MCP client For research and analysis ### Ask your own files Index a collection with Ollama embeddings and retrieval stays as local as the chat model does. Chat with your documents ## Point it at the model you already run Free and open source. No account, no key needed for Ollama or LM Studio. [Download Conduit](https://conduitllm.com/#get) [Read the setup docs](https://conduitllm.com/docs.html) A release candidate: installers aren't OS code-signed yet, so expect a SmartScreen or Gatekeeper prompt on first launch.