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 #1625] Is there a way to install ollama and download models on a external SSD on mac M1 ? #902

New Issue
Closed
opened 2026-04-12 10:34:44 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 10:34:44 -05:00
Owner
Copy Link

Originally created by @pramitsawant on GitHub (Dec 20, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1625

On Macbook Pro M1
The models are downloaded to this path /Users/{username}/.ollama/models/manifests/registry.ollama.ai/library

I use a external ssd where i download and keep all less recently used apps and other files.

can we have an option to set model download path ?

Originally created by @pramitsawant on GitHub (Dec 20, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1625 On Macbook Pro M1 The models are downloaded to this path /Users/{username}/.ollama/models/manifests/registry.ollama.ai/library I use a external ssd where i download and keep all less recently used apps and other files. can we have an option to set model download path ?
GiteaMirror commented 2026-04-12 10:34:47 -05:00
Author
Owner
Copy Link

@mattbisme commented on GitHub (Dec 20, 2023):

This is a good idea. I don't seem to recall a configuration option for putting the models on another location.

<!-- gh-comment-id:1864917889 --> @mattbisme commented on GitHub (Dec 20, 2023): This is a good idea. I don't seem to recall a configuration option for putting the models on another location.
GiteaMirror commented 2026-04-12 10:34:48 -05:00
Author
Owner
Copy Link

@justinh-rahb commented on GitHub (Dec 20, 2023):

In the meantime, you could use LM Studio to download and store models elsewhere and create custom modelfiles to import them. You won't have the advantage of the ollama model download management of course, but it'll accomplish your goal.

<!-- gh-comment-id:1865048590 --> @justinh-rahb commented on GitHub (Dec 20, 2023): In the meantime, you could use LM Studio to download and store models elsewhere and create custom modelfiles to import them. You won't have the advantage of the ollama model download management of course, but it'll accomplish your goal.
GiteaMirror commented 2026-04-12 10:34:49 -05:00
Author
Owner
Copy Link

@prantlf commented on GitHub (Dec 21, 2023):

You could try symlinking ~/.ollama to your external disk.

<!-- gh-comment-id:1866103601 --> @prantlf commented on GitHub (Dec 21, 2023): You could try symlinking `~/.ollama` to your external disk.
GiteaMirror commented 2026-04-12 10:34:50 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Dec 22, 2023):

Symlinking ~/.ollama or ~/.ollama/models is the best way to go right now.

The ollama app will use the value of the OLLAMA_MODELS environment variable if you launch it from a shell like soOLLAMA_MODELS=DIRPATH start /Applications/Ollama.app , but the problem is that there is no good way to set the variable that works across restarts. You have to disable the normal Launch at Login functionality and instead set up your own launchd job.

<!-- gh-comment-id:1867136337 --> @easp commented on GitHub (Dec 22, 2023): Symlinking ~/.ollama or ~/.ollama/models is the best way to go right now. The ollama app will use the value of the OLLAMA_MODELS environment variable if you launch it from a shell like so`OLLAMA_MODELS=DIRPATH start /Applications/Ollama.app` , but the problem is that there is no good way to set the variable that works across restarts. You have to disable the normal Launch at Login functionality and instead set up your own launchd job.
GiteaMirror commented 2026-04-12 10:34:51 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Jan 3, 2024):

hi @pramitsawant It looks like the comment from @easp solves your issue. That is, in fact, the right way to achieve this. I'll go ahead and close this issue, but if you still have a problem, reopen, and we can continue to look at it. There is a FAQ in the Ollama docs that covers how to set environment variables on different platforms. Thanks so much for being part of this great community.

<!-- gh-comment-id:1875883233 --> @technovangelist commented on GitHub (Jan 3, 2024): hi @pramitsawant It looks like the comment from @easp solves your issue. That is, in fact, the right way to achieve this. I'll go ahead and close this issue, but if you still have a problem, reopen, and we can continue to look at it. There is a FAQ in the Ollama docs that covers how to set environment variables on different platforms. Thanks so much for being part of this great community.
GiteaMirror commented 2026-04-12 10:34:52 -05:00
Author
Owner
Copy Link

@hasandenizuk commented on GitHub (Feb 23, 2024):

Any updates on this? I have a full C drive
edit: Solved: https://github.com/ollama/ollama/issues/2551

<!-- gh-comment-id:1962133809 --> @hasandenizuk commented on GitHub (Feb 23, 2024): Any updates on this? I have a full C drive edit: **Solved**: https://github.com/ollama/ollama/issues/2551
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#902
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?