From d0f3a8f838354f30c8ce1720dbe34023435eff04 Mon Sep 17 00:00:00 2001 From: Vishal Kumar Singh Date: Wed, 24 Jun 2026 22:31:30 +0530 Subject: [PATCH] docs: clarify local Ollama setup --- packages/kilo-docs/pages/ai-providers/ollama.md | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/packages/kilo-docs/pages/ai-providers/ollama.md b/packages/kilo-docs/pages/ai-providers/ollama.md index a2782d9c451..621776fbfed 100644 --- a/packages/kilo-docs/pages/ai-providers/ollama.md +++ b/packages/kilo-docs/pages/ai-providers/ollama.md @@ -10,6 +10,12 @@ Kilo Code supports running models locally using Ollama. This provides privacy, o **Website:** [https://ollama.com/](https://ollama.com/) +{% callout type="info" title="Local Ollama vs. Ollama Cloud" %} +Use the **Ollama** provider for a local Ollama daemon started with `ollama serve`. Local models use the `ollama/` format, for example `ollama/qwen3-coder:30b`, and connect to your local base URL. + +**Ollama Cloud** appears in Kilo Gateway and BYOK flows. It is a hosted provider path and does not connect to `http://localhost:11434`. +{% /callout %} + @@ -68,7 +74,7 @@ You need to have at least 32k to get decent results, but increasing the context To configure the context window, set "Context Window Size (num_ctx)" in the API Provider settings. -### Configure the Timout +### Configure the Timeout By default, API requests time out after 10 minutes. Local models can be slow, if you hit this timeout you can consider increasing it here: VS Code Extensions panel > Kilo Code gear menu > Settings > API Request Timeout. @@ -95,6 +101,8 @@ The extension stores this in your `kilo.json` config file. You can also edit the Ollama runs locally, so no API key is needed. Configure the base URL if Ollama is running on a different host: +Use `ollama/` for the selected model. If you see `ollama-cloud/...`, you are using the hosted Kilo Gateway/BYOK provider instead of your local Ollama server. + **Config file** (`~/.config/kilo/kilo.json` or `./kilo.json`): ```jsonc