github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #338] More reliable model pull #150

New Issue
Closed
opened 2026-04-12 09:40:57 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 09:40:57 -05:00
Owner
Copy Link

Originally created by @bohdyone on GitHub (Aug 14, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/338

Hi guys,

On Mac OS 13.4.1 and have been having some trouble downloading the larger models.

I get occasional "unexpected EOF" issues and sometimes when the model is fully downloaded it is detected as corrupted and must be downloaded again. Some of this seems to be to do with system sleep interrupting the download, where it gets stuck and must be aborted and then resumed.

Is it possible to improve the reliability and resumability of downloads somewhat?

Some suggestions:

  1. Prevent system sleep (where possible) during model download
  2. Use some sort of block-based hashing (e.g. Merkle tree) to detect corrupted blocks when resuming downloads

Thanks.

Originally created by @bohdyone on GitHub (Aug 14, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/338 Hi guys, On Mac OS 13.4.1 and have been having some trouble downloading the larger models. I get occasional "unexpected EOF" issues and sometimes when the model is fully downloaded it is detected as corrupted and must be downloaded again. Some of this seems to be to do with system sleep interrupting the download, where it gets stuck and must be aborted and then resumed. Is it possible to improve the reliability and resumability of downloads somewhat? Some suggestions: 1. Prevent system sleep (where possible) during model download 1. Use some sort of block-based hashing (e.g. Merkle tree) to detect corrupted blocks when resuming downloads Thanks.
GiteaMirror added the bug label 2026-04-12 09:40:57 -05:00
GiteaMirror commented 2026-04-12 09:40:59 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Aug 22, 2023):

@bohdyone Thanks for sending this in. We've been making background changes to this as we see the issues come. There is so much more to improve on the performance of downloading/uploading models on Ollama. Much more to come on this.

Closing this issue for now since we are already making the changes.

If you do see more, please try to give us the logs so we can troubleshoot. This will get improved overtime.

Thank you so much for sending this in.

<!-- gh-comment-id:1687262078 --> @mchiang0610 commented on GitHub (Aug 22, 2023): @bohdyone Thanks for sending this in. We've been making background changes to this as we see the issues come. There is so much more to improve on the performance of downloading/uploading models on Ollama. Much more to come on this. Closing this issue for now since we are already making the changes. If you do see more, please try to give us the logs so we can troubleshoot. This will get improved overtime. Thank you so much for sending this in.
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#150
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?