How to use Ollama with OpenCode (local models, 2026)

ollama launch opencode or one opencode.json block, plus the 64k context OpenCode requires, why tool calls fail without it, and what fits on your GPU…

Aliteq
Priya Nair · Software & Systems Editor

The short answer

Run ollama launch opencode. Ollama starts OpenCode with an inline config for the model you pick and leaves your own opencode.json alone. To set it up by hand, add an ollama provider to opencode.json…

Fastest: ollama launch opencode

Manual: an ollama provider block in opencode.json

Required: 64k+ context. Ollama's default is 4k on sub-24 GiB GPUs.

Tool calls failing? Raise the context before you blame the model

Aliteq

Read the full story

How to use Ollama with OpenCode (local models, 2026)

Read the full story on Aliteq