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 #6589] Can this be used with "LM Studio" to share models? If so, how can it be modified? #4147

New Issue
Closed
opened 2026-04-12 15:03:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 15:03:31 -05:00
Owner
Copy Link

Originally created by @Willy-Shenn on GitHub (Sep 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6589

I am currently using two UI systems, but they cannot share models (possibly due to differences in how the models are identified and created). Even after modifying the environment variables, both UIs cannot use models from the same path. Is there anyone who can guide me on how to modify the two UIs so they can use models from the same path? I would be very grateful.

Originally created by @Willy-Shenn on GitHub (Sep 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6589 I am currently using two UI systems, but they cannot share models (possibly due to differences in how the models are identified and created). Even after modifying the environment variables, both UIs cannot use models from the same path. Is there anyone who can guide me on how to modify the two UIs so they can use models from the same path? I would be very grateful.
GiteaMirror commented 2026-04-12 15:03:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 2, 2024):

LM Studio works with GGUF files, so this would seem theoretically possible. You would just need to identify the GGUF files and then provide a reference to LM Studio to allow it to find and load the model.

If you are on linux (and maybe Mac) the following script will find all GGUF files of models downloaded from the main ollama library (not community supplied models but that can be done by adjusting paths) and prints the path to the GGUF file and it's name.

OLLAMA_MODELS=/path/to/ollama/models
find $OLLAMA_MODELS/manifests/registry.ollama.ai/library -type f | while read i ; do 
  jq -r \
    --arg models "${OLLAMA_MODELS%/}" \
    --arg name "${i#*/library/}" \
    '.layers[]|select(.mediaType=="application/vnd.ollama.image.model")|"\(.digest)"|gsub(":";"-")|"\($name|gsub("/";":")) \($models)/blobs/\(.)"' \
    "$i"
done

On a unix-y system you can then link the model by name to the corresponding GGUF file:

LMSTUDIO_MODELS=/some/path/here
./find-gguf | while read name path  ; do
  ln -s "$path" "$LMSTUDIO_MODELS/$name"
done

I don't use LM Studio so I don't know if it has central repo, YMMV.

<!-- gh-comment-id:2325254559 --> @rick-github commented on GitHub (Sep 2, 2024): LM Studio works with GGUF files, so this would seem theoretically possible. You would just need to identify the GGUF files and then provide a reference to LM Studio to allow it to find and load the model. If you are on linux (and maybe Mac) the following script will find all GGUF files of models downloaded from the main ollama library (not community supplied models but that can be done by adjusting paths) and prints the path to the GGUF file and it's name. ```sh OLLAMA_MODELS=/path/to/ollama/models find $OLLAMA_MODELS/manifests/registry.ollama.ai/library -type f | while read i ; do jq -r \ --arg models "${OLLAMA_MODELS%/}" \ --arg name "${i#*/library/}" \ '.layers[]|select(.mediaType=="application/vnd.ollama.image.model")|"\(.digest)"|gsub(":";"-")|"\($name|gsub("/";":")) \($models)/blobs/\(.)"' \ "$i" done ``` On a unix-y system you can then link the model by name to the corresponding GGUF file: ```sh LMSTUDIO_MODELS=/some/path/here ./find-gguf | while read name path ; do ln -s "$path" "$LMSTUDIO_MODELS/$name" done ``` I don't use LM Studio so I don't know if it has central repo, YMMV.
GiteaMirror commented 2026-04-12 15:03:36 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 2, 2024):

@Willy-Shenn as Rick mentioned, it should in theory be possible, but it's definitely not "supported". Is there a feature in LM Studio which is missing in Ollama?

I'm going to close the issue, but feel free to comment.

<!-- gh-comment-id:2325331364 --> @pdevine commented on GitHub (Sep 2, 2024): @Willy-Shenn as Rick mentioned, it should in theory be possible, but it's definitely not "supported". Is there a feature in LM Studio which is missing in Ollama? I'm going to close the issue, but feel free to comment.
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
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#4147
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?