github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7751] List of all available models #30708

New Issue
Closed
opened 2026-04-22 10:36:40 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 10:36:40 -05:00
Owner
Copy Link

Originally created by @vt-alt on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7751

Please provide list of (or API to list) all models available on https://ollama.com/library with tags.
This would be useful for users to get them from cli without a browser.
Also, this would be useful for shell completions.

Originally created by @vt-alt on GitHub (Nov 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7751 Please provide list of (or API to list) all models available on https://ollama.com/library with tags. This would be useful for users to get them from cli without a browser. Also, this would be useful for shell completions.
GiteaMirror added the feature request label 2026-04-22 10:36:40 -05:00
GiteaMirror commented 2026-04-22 10:36:41 -05:00
Author
Owner
Copy Link

@vt-alt commented on GitHub (Nov 20, 2024):

I see that request is reappearing. Models list could be just a file without internet access packed on every release into docs.

<!-- gh-comment-id:2487056405 --> @vt-alt commented on GitHub (Nov 20, 2024): I see that request is reappearing. Models list could be just a file without internet access packed on every release into docs.
GiteaMirror commented 2026-04-22 10:36:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 20, 2024):

Until the API is implemented, https://github.com/ollama/ollama/issues/7239#issuecomment-2423530279 has some code that scrapes the library.

<!-- gh-comment-id:2487139779 --> @rick-github commented on GitHub (Nov 20, 2024): Until the API is implemented, https://github.com/ollama/ollama/issues/7239#issuecomment-2423530279 has some code that scrapes the library.
GiteaMirror commented 2026-04-22 10:36:41 -05:00
Author
Owner
Copy Link

@kth8 commented on GitHub (Nov 20, 2024):

I've been using these 2 one liners in a justfile to quickly get models and tags

set positional-arguments := true

default:
  just --list

#list Ollama models
@models:
    curl -s https://ollama.com/library | grep -oP 'href="/library/\K[^"]+'

#list model tags
@tags model:
    curl -s https://ollama.com/library/$1/tags | grep -o "$1:[^\" ]*q[^\" ]*" | grep -E -v 'text|base|fp|q[45]_[01]'

$ just models
qwen2.5-coder
llama3.2-vision
llama3.2
llama3.1
llama3
mistral
...

$ just tags llama3.2
llama3.2:1b-instruct-q2_K
llama3.2:1b-instruct-q3_K_L
llama3.2:1b-instruct-q3_K_M
llama3.2:1b-instruct-q3_K_S
llama3.2:1b-instruct-q4_K_M
llama3.2:1b-instruct-q4_K_S
llama3.2:1b-instruct-q5_K_M
llama3.2:1b-instruct-q5_K_S
llama3.2:1b-instruct-q6_K
llama3.2:1b-instruct-q8_0
llama3.2:3b-instruct-q2_K
llama3.2:3b-instruct-q3_K_L
llama3.2:3b-instruct-q3_K_M
llama3.2:3b-instruct-q3_K_S
llama3.2:3b-instruct-q4_K_M
llama3.2:3b-instruct-q4_K_S
llama3.2:3b-instruct-q5_K_M
llama3.2:3b-instruct-q5_K_S
llama3.2:3b-instruct-q6_K
llama3.2:3b-instruct-q8_0
<!-- gh-comment-id:2488290937 --> @kth8 commented on GitHub (Nov 20, 2024): I've been using these 2 one liners in a [justfile](https://github.com/casey/just) to quickly get models and tags ``` set positional-arguments := true default: just --list #list Ollama models @models: curl -s https://ollama.com/library | grep -oP 'href="/library/\K[^"]+' #list model tags @tags model: curl -s https://ollama.com/library/$1/tags | grep -o "$1:[^\" ]*q[^\" ]*" | grep -E -v 'text|base|fp|q[45]_[01]' ``` ``` $ just models qwen2.5-coder llama3.2-vision llama3.2 llama3.1 llama3 mistral ... $ just tags llama3.2 llama3.2:1b-instruct-q2_K llama3.2:1b-instruct-q3_K_L llama3.2:1b-instruct-q3_K_M llama3.2:1b-instruct-q3_K_S llama3.2:1b-instruct-q4_K_M llama3.2:1b-instruct-q4_K_S llama3.2:1b-instruct-q5_K_M llama3.2:1b-instruct-q5_K_S llama3.2:1b-instruct-q6_K llama3.2:1b-instruct-q8_0 llama3.2:3b-instruct-q2_K llama3.2:3b-instruct-q3_K_L llama3.2:3b-instruct-q3_K_M llama3.2:3b-instruct-q3_K_S llama3.2:3b-instruct-q4_K_M llama3.2:3b-instruct-q4_K_S llama3.2:3b-instruct-q5_K_M llama3.2:3b-instruct-q5_K_S llama3.2:3b-instruct-q6_K llama3.2:3b-instruct-q8_0 ```
GiteaMirror commented 2026-04-22 10:36:42 -05:00
Author
Owner
Copy Link

@vt-alt commented on GitHub (Nov 20, 2024):

I've been using these 2 one liners in a justfile to quickly get models and tags

Thanks. Wow but it's so slow and definitely not suitable for bash completions as run-time http requests. But of course, list could be prepared in advance.

<!-- gh-comment-id:2489599707 --> @vt-alt commented on GitHub (Nov 20, 2024): > I've been using these 2 one liners in a [justfile](https://github.com/casey/just) to quickly get models and tags Thanks. Wow but it's so slow and definitely not suitable for bash completions as run-time http requests. But of course, list could be prepared in advance.
GiteaMirror commented 2026-04-22 10:36:42 -05:00
Author
Owner
Copy Link

@kth8 commented on GitHub (Nov 21, 2024):

Scraping the whole library takes 0.8s and tags take 0.3s from my benchmark

$ hyperfine "just models"
Benchmark 1: just models
  Time (mean ± σ):     813.1 ms ±  79.3 ms    [User: 51.7 ms, System: 14.7 ms]
  Range (min … max):   634.0 ms … 887.5 ms    10 runs

$ hyperfine "just tags llama3.2"
Benchmark 1: just tags llama3.2
  Time (mean ± σ):     285.3 ms ±  87.1 ms    [User: 50.9 ms, System: 14.9 ms]
  Range (min … max):   199.6 ms … 530.8 ms    11 runs

I'm not trying to use this for autocomplete, mainly used it for automated benchmarking

Ollama-MMLU-Pro $ just tags llama3.2 > models.txt
Ollama-MMLU-Pro $ while read line; do ollama pull $line; pipenv run python run_openai.py -u http://127.0.0.1:11434/v1 -p 3 --category other -m $line; done < models.txt
<!-- gh-comment-id:2489902070 --> @kth8 commented on GitHub (Nov 21, 2024): Scraping the whole library takes 0.8s and tags take 0.3s from my benchmark ``` $ hyperfine "just models" Benchmark 1: just models Time (mean ± σ): 813.1 ms ± 79.3 ms [User: 51.7 ms, System: 14.7 ms] Range (min … max): 634.0 ms … 887.5 ms 10 runs $ hyperfine "just tags llama3.2" Benchmark 1: just tags llama3.2 Time (mean ± σ): 285.3 ms ± 87.1 ms [User: 50.9 ms, System: 14.9 ms] Range (min … max): 199.6 ms … 530.8 ms 11 runs ``` I'm not trying to use this for autocomplete, mainly used it for automated benchmarking ``` Ollama-MMLU-Pro $ just tags llama3.2 > models.txt Ollama-MMLU-Pro $ while read line; do ollama pull $line; pipenv run python run_openai.py -u http://127.0.0.1:11434/v1 -p 3 --category other -m $line; done < models.txt ```
GiteaMirror commented 2026-04-22 10:36:42 -05:00
Author
Owner
Copy Link

@vt-alt commented on GitHub (Nov 21, 2024):

Yes now it's much faster, perhaps some glitch at the time I tested it. Thanks

<!-- gh-comment-id:2489913082 --> @vt-alt commented on GitHub (Nov 21, 2024): Yes now it's much faster, perhaps some glitch at the time I tested it. Thanks
GiteaMirror commented 2026-04-22 10:36:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 21, 2024):

Looks like a dup of #286

<!-- gh-comment-id:2491844816 --> @dhiltgen commented on GitHub (Nov 21, 2024): Looks like a dup of #286
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#30708
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?