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 #11290] Question regarding fetching model information without downloading entire model #53959

New Issue
Closed
opened 2026-04-29 05:00:45 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 05:00:45 -05:00
Owner
Copy Link

Originally created by @zbhavyai on GitHub (Jul 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11290

Hi,

Is there a way (or are there any plans) to expose model metadata such as capabilities, without downloading the entire model?

Currently, the only way I know to check this is:

curl -sSf -X POST localhost:11434/api/show -d '{"model": "moondream:1.8b"}' | jq -r '.capabilities'

or

ollama show moondream:1.8b | grep -A3 'Capabilities'

Both of these works great, but only if the model is already downloaded locally.

So, is there something like -

  • A --metadata-only or --dry-run flag to ollama pull
  • An official public API endpoint for the model library
  • Partial download of the manifest layer only

It would be incredibly useful for managing models dynamically and avoiding unnecessary downloads.

Originally created by @zbhavyai on GitHub (Jul 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11290 Hi, Is there a way (or are there any plans) to expose model metadata such as capabilities, without downloading the entire model? Currently, the only way I know to check this is: ```shell curl -sSf -X POST localhost:11434/api/show -d '{"model": "moondream:1.8b"}' | jq -r '.capabilities' ``` or ```shell ollama show moondream:1.8b | grep -A3 'Capabilities' ``` Both of these works great, *but only if the model is already downloaded locally*. So, is there something like - * A `--metadata-only` or `--dry-run` flag to `ollama pull` * An official public API endpoint for the model library * Partial download of the manifest layer only It would be incredibly useful for managing models dynamically and avoiding unnecessary downloads.
GiteaMirror added the feature request label 2026-04-29 05:00:45 -05:00
GiteaMirror commented 2026-04-29 05:00:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 3, 2025):

#286

<!-- gh-comment-id:3033551243 --> @rick-github commented on GitHub (Jul 3, 2025): #286
GiteaMirror commented 2026-04-29 05:00:48 -05:00
Author
Owner
Copy Link

@zbhavyai commented on GitHub (Jul 4, 2025):

#286

Ah thanks!

<!-- gh-comment-id:3037155720 --> @zbhavyai commented on GitHub (Jul 4, 2025): > [#286](https://github.com/ollama/ollama/issues/286) Ah thanks!
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#53959
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?