Setup guide - Documented by Continue
Use Ollama in Continue
Continue has a native provider: ollama model entry in config.yaml; set the model to an Ollama model id and apiBase only if Ollama runs remotely.
Last verified 4 steps2 official sources
Steps
- Step 1.
Pull a model in Ollama (model id from Ollama's docs).
Terminalollama pull qwen3.5 - Step 2.
Add an Ollama model to your Continue config (YAML).
YAMLname: My Config version: 0.0.1 schema: v1 models: - name: <MODEL_NAME> provider: ollama model: <MODEL_ID> apiBase: http://<my endpoint>:11434 # if running a remote instance of Ollama - Step 3.
If tools or images do not work with a custom model name, set capabilities explicitly.
YAMLmodels: - name: <CUSTOM_MODEL_NAME> provider: ollama model: <CUSTOM_MODEL_ID> capabilities: - tool_use # Enable if your model supports function calling - image_input # Enable for vision models - Step 4.
If you see "Model requires more system memory", reduce contextLength.
YAMLmodels: - name: Deepseek R1 provider: ollama model: deepseek-r1:latest defaultCompletionOptions: contextLength: 2048
Caveats
- Ollama's docs have no Continue page; config comes from Continue's docs, which use placeholders for the model id. The qwen3.5 model id is taken from Ollama's integration docs and combined here.
- apiBase is only needed for a remote Ollama instance; the base URL shown is Ollama's documented default local endpoint.
- Continue may set a higher default context length than other Ollama tools, which can cause the system memory error.
More setup guides
Same tool, other providers
Related reading
- Ollama Decision Models: Run Nimble Locally with --askOllama 0.40.4 runs decision models locally: ollama run nimble --ask answers yes/no, label and score questions with probabilities. Commands and limits.
- Ollama 0.40 on Mac: MLX by Default, Disk Space DoubledOllama 0.40 runs supported models on MLX on Apple Silicon and keeps a backup copy of each model you load. What it costs in disk, what is fixed, and the cleanup.
- GitHub Copilot CLI With Ollama: Local Models and the New SandboxCopilot CLI 1.0.94 finds local Ollama models from /model and ships an OS-level sandbox. Setup, the 4k context trap, and why local is not offline.
- Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClawHermes Agent is Nous Research's open-source, self-improving AI agent. Run it locally with Ollama, see how its skills system works, and compare it with OpenClaw.
- What Is OpenClaw? Setup, Skills, MCP Server, Claude Code, and Ollama (2026 Guide)What is OpenClaw? A self-hosted personal AI agent you reach through chat apps. Install, skills and ClawHub, its MCP server, Claude Code use, and Ollama models.
- GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOKGitHub Copilot for JetBrains adds memory across chat sessions, Ollama as a BYOK provider, and enterprise settings for MCP access. What each feature does.
FAQ
How do I use Ollama in Continue?
Continue has a native provider: ollama model entry in config.yaml; set the model to an Ollama model id and apiBase only if Ollama runs remotely.
Which Ollama model ids work in Continue?
The official docs read for this guide list qwen3.5 and deepseek-r1:latest. Requests go to http://localhost:11434.
Is this an official Ollama and Continue setup?
Continue documents this setup in its own docs. It was last checked against 2 official pages on October 17, 2026.
Sources
Last verified against 2 official pages.
- docs.continue.devhttps://docs.continue.dev/customize/model-providers/top-level/ollama
- docs.ollama.comhttps://docs.ollama.com/integrations/opencode
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.