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 #11876] New app: remember last-used model #33642

New Issue
Closed
opened 2026-04-22 16:31:34 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 16:31:34 -05:00
Owner
Copy Link

Originally created by @pstashp on GitHub (Aug 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11876

Originally assigned to: @BruceMacD on GitHub.

In the new desktop app, it should:

  • New chat: use last-used model (or user-defined setting), instead of always back to gpt-oss
  • Existing chat: remember what model was used in the last prompt in the chat, and set it to that
Originally created by @pstashp on GitHub (Aug 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11876 Originally assigned to: @BruceMacD on GitHub. In the new desktop app, it should: - **New chat:** use last-used model (or user-defined setting), instead of always back to `gpt-oss` - **Existing chat:** remember what model was used in the last prompt in the chat, and set it to that
GiteaMirror added the bug label 2026-04-22 16:31:34 -05:00
GiteaMirror commented 2026-04-22 16:31:37 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Aug 13, 2025):

@pstashp which version / platform are you using Ollama on? It is supposed to work that way, but I think there's just a bug.

<!-- gh-comment-id:3184978401 --> @pdevine commented on GitHub (Aug 13, 2025): @pstashp which version / platform are you using Ollama on? It is supposed to work that way, but I think there's just a bug.
GiteaMirror commented 2026-04-22 16:31:37 -05:00
Author
Owner
Copy Link

@novkel commented on GitHub (Aug 13, 2025):

Same here (Windows 10 x64 22h2 - Ollama 0.11.4).
I have installed model gpt-oss:20b and it still selected even after using another model.
gpt-oss:120b is on top of the list (but not selected) while i never installed it. There is no alphanumeric sort for these two.

<!-- gh-comment-id:3185569545 --> @novkel commented on GitHub (Aug 13, 2025): Same here (Windows 10 x64 22h2 - Ollama 0.11.4). I have installed model gpt-oss:20b and it still selected even after using another model. gpt-oss:120b is on top of the list (but not selected) while i never installed it. There is no alphanumeric sort for these two.
GiteaMirror commented 2026-04-22 16:31:37 -05:00
Author
Owner
Copy Link

@novkel commented on GitHub (Aug 15, 2025):

The 0.11.5 pre-release correct some points :

  • Alphanumeric sort is now ok.
  • Old chat remember used model.

There is still :

  • gpt-oss:120b still in the list (and some qwen3 model too), more of this issue -> https://github.com/ollama/ollama/issues/11789
  • If I select an old chat with gemma3 model for instance, a new chat is now preselect with gemma3. If I relaunch Ollama, gpt-oss:20b is preselect again.
<!-- gh-comment-id:3190649690 --> @novkel commented on GitHub (Aug 15, 2025): The 0.11.5 pre-release correct some points : - Alphanumeric sort is now ok. - Old chat remember used model. There is still : - gpt-oss:120b still in the list (and some qwen3 model too), more of this issue -> [https://github.com/ollama/ollama/issues/11789](url) - If I select an old chat with gemma3 model for instance, a new chat is now preselect with gemma3. If I relaunch Ollama, gpt-oss:20b is preselect again.
GiteaMirror commented 2026-04-22 16:31:38 -05:00
Author
Owner
Copy Link

@mrs83 commented on GitHub (Aug 18, 2025):

Additionally if you plan to expand the UI functionalities as LM Studio does, it would be beneficial to give users the option to select a different default model setting. During onboarding, LM Studio suggests gpt-oss, but does not enforce it.

<!-- gh-comment-id:3196572774 --> @mrs83 commented on GitHub (Aug 18, 2025): Additionally if you plan to expand the UI functionalities as LM Studio does, it would be beneficial to give users the option to select a different default model setting. During onboarding, LM Studio suggests gpt-oss, but does not enforce it.
GiteaMirror commented 2026-04-22 16:31:39 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Aug 20, 2025):

Hey everyone, thanks for all the feedback. This should be fixed in the new release. Closing this as the reported bug has been closed, but still open and happy to receive other feedback to keep iterating on the experience here.

<!-- gh-comment-id:3208094539 --> @BruceMacD commented on GitHub (Aug 20, 2025): Hey everyone, thanks for all the feedback. This should be fixed in the new release. Closing this as the reported bug has been closed, but still open and happy to receive other feedback to keep iterating on the experience here.
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 bug
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#33642
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?