microsoft / microsoft/foundry-dev-tools

Remote Ollama models cannot be managed

Open
#317 3 comments 0 reactions 1 assignee View on GitHub

@QinghuiMeng-M is already working on this.

Since Dec 9, 2025.

investigating
Dominant language
JavaScript
Stars
2.1k
Forks
260
Avg merge
42m
Merged PRs (30d)
29

Description

Hey All. I have a remote Ollama instance with models that I want to use for copilot chat, inline completion, etc.

It seems that remote Ollama models to not show up in the "Manage Language Models" picker, which would allow me to select them as models to use for chat and other applications. Remote models work perfectly well in the model playground.

Oddly, when I am running a local instance of Ollama, those models do show up in the picker.

In the below image, deepseek-r1:1.5b is running on local Ollama, and deepseek-r1:8b is running on remote Ollama, but only 1.5b is selectable in the "Manage Language Models" picker.

Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.