github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11955] Allow Users to Set a Default Model or Remove Default UI Selection #69997

New Issue
Closed
opened 2026-05-04 20:01:43 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 20:01:43 -05:00
Owner
Copy Link

Originally created by @mrs83 on GitHub (Aug 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11955

Currently the Ollama UI seems to default to selecting gpt-oss:20b as the model.

I would like to request a feature that either removes this default selection or allows the user to specify their own default model.

The ability to choose a preferred model would greatly improve the user experience for those who primarily use Ollama as a local endpoint for other applications.

Having to manually switch away from gpt-oss each time is a minor friction point.

This feature would be similar to how modern operating systems allow users to set a default web browser.

Why it's important?

  • It gives users more control over their environment and allows them to tailor Ollama to their specific workflow
  • It streamlines the process for users who work with models other than gpt-oss, saving them an extra step.
  • It positions Ollama as a neutral platform for all supported models, rather than giving preferential treatment to one
  • It prevents users with limited or metered internet access from accidentally initiating a large, unwanted model download.

I also noticed that if I relaunch the UI, the last selected model is not remembered.

This practice, combined with the default selection, could be perceived as a marketing campaign to make gpt-oss the most downloaded model.

While I congratulate OpenAI on the significant achievement of releasing an open-weights model, I am concerned that this approach will unintentionally shift community focus away from Ollama

Thank you for considering this request 👍

Originally created by @mrs83 on GitHub (Aug 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11955 Currently the Ollama UI seems to default to selecting gpt-oss:20b as the model. I would like to request a feature that either removes this default selection or allows the user to specify their own default model. The ability to choose a preferred model would greatly improve the user experience for those who primarily use Ollama as a local endpoint for other applications. Having to manually switch away from gpt-oss each time is a minor friction point. This feature would be similar to how modern operating systems allow users to set a default web browser. Why it's important? - It gives users more control over their environment and allows them to tailor Ollama to their specific workflow - It streamlines the process for users who work with models other than gpt-oss, saving them an extra step. - It positions Ollama as a neutral platform for all supported models, rather than giving preferential treatment to one - It prevents users with limited or metered internet access from accidentally initiating a large, unwanted model download. I also noticed that if I relaunch the UI, the last selected model is not remembered. This practice, combined with the default selection, could be perceived as a marketing campaign to make gpt-oss the most downloaded model. While I congratulate OpenAI on the significant achievement of releasing an open-weights model, I am concerned that this approach will unintentionally shift community focus away from Ollama Thank you for considering this request 👍
GiteaMirror added the feature request label 2026-05-04 20:01:43 -05:00
GiteaMirror commented 2026-05-04 20:01:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 18, 2025):

#11876

<!-- gh-comment-id:3195979694 --> @rick-github commented on GitHub (Aug 18, 2025): #11876
GiteaMirror commented 2026-05-04 20:01:48 -05:00
Author
Owner
Copy Link

@mrs83 commented on GitHub (Aug 19, 2025):

In any case, when a project like Ollama, which has done so much to make local AI accessible, defaults to an OpenAI model, it gives more visibility and attention to a company that already has an unfair advantage.

The community is pouring personal time and resources into building ecosystems for ethical, local and private LLMs, and they're doing this silently and without massive funding or international headlines.

This comes at the expense of amazing open-source releases from the community, such as Hugging Face's SmolLM3, which represents the kind of efficient and accessible LLM that many of us are dedicated to fine-tune.

Could you please consider changing this behavior? An ideal solution would be to not have a default selection at all, or to allow users to set their own preferred default model.

<!-- gh-comment-id:3200273487 --> @mrs83 commented on GitHub (Aug 19, 2025): In any case, when a project like Ollama, which has done so much to make local AI accessible, defaults to an OpenAI model, it gives more visibility and attention to a company that already has an unfair advantage. The community is pouring personal time and resources into building ecosystems for ethical, local and private LLMs, and they're doing this silently and without massive funding or international headlines. This comes at the expense of amazing open-source releases from the community, such as Hugging Face's [SmolLM3](https://github.com/ollama/ollama/issues/11340), which represents the kind of efficient and accessible LLM that many of us are dedicated to fine-tune. Could you please consider changing this behavior? An ideal solution would be to not have a default selection at all, or to allow users to set their own preferred default model.
GiteaMirror commented 2026-05-04 20:01:50 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Aug 19, 2025):

@mrs83 definitely appreciate the feedback. I'm going to close this as a dupe of #11876 though.

<!-- gh-comment-id:3202711571 --> @pdevine commented on GitHub (Aug 19, 2025): @mrs83 definitely appreciate the feedback. I'm going to close this as a dupe of #11876 though.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#69997
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?