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 #12750] Trying to pull models does not work on multiple machines #8454

New Issue
Closed
opened 2026-04-12 21:08:21 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 21:08:21 -05:00
Owner
Copy Link

Originally created by @simonaden on GitHub (Oct 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12750

What is the issue?

I am from Germany and own the Macbook Pro M1 with the M1 Pro chip and an windows machine with Windows 10, i7-4770, 32 GB RAM and the GTX 1070 running docker. On windows I run ollama inside docker with the latest image and docker version 4.48.0

When I try to run "ollama pull model", the download starts but after a little while the download speed goes to zero. and the following error occures:

"...part 2 stalled; retrying. If this persists, press ctrl-c to exit, then 'ollama pull' to find a faster connection."

Even after doing ctrl+c multiple times I am only able to get the download to 100%, but the model is not being installed so not usable.

This issue exists on both machines and in totally different locations(Home, University or Work) and for all models I tried to download (qwen3:4b, llama3.1:8b, gemma3:4b, ...). I would guess it's the same for all models.

Previously it worked on both machines without any issues, like 3 days ago. So I am wondering if this is some Issue on my end or if there is some issue with ollama in Germany.

Relevant log output

..part 2 stalled; retrying. If this persists, press ctrl-c to exit, then 'ollama pull' to find a faster connection.

OS

No response

GPU

No response

CPU

No response

Ollama version

ollama version is 0.12.6 on both machines

Originally created by @simonaden on GitHub (Oct 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12750 ### What is the issue? I am from Germany and own the Macbook Pro M1 with the M1 Pro chip and an windows machine with Windows 10, i7-4770, 32 GB RAM and the GTX 1070 running docker. On windows I run ollama inside docker with the latest image and docker version 4.48.0 When I try to run "ollama pull model", the download starts but after a little while the download speed goes to zero. and the following error occures: "...part 2 stalled; retrying. If this persists, press ctrl-c to exit, then 'ollama pull' to find a faster connection." Even after doing ctrl+c multiple times I am only able to get the download to 100%, but the model is not being installed so not usable. This issue exists on both machines and in totally different locations(Home, University or Work) and for all models I tried to download (qwen3:4b, llama3.1:8b, gemma3:4b, ...). I would guess it's the same for all models. Previously it worked on both machines without any issues, like 3 days ago. So I am wondering if this is some Issue on my end or if there is some issue with ollama in Germany. ### Relevant log output ```shell ..part 2 stalled; retrying. If this persists, press ctrl-c to exit, then 'ollama pull' to find a faster connection. ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version ollama version is 0.12.6 on both machines
GiteaMirror added the bug label 2026-04-12 21:08:21 -05:00
GiteaMirror commented 2026-04-12 21:08:24 -05:00
Author
Owner
Copy Link

@simonaden commented on GitHub (Oct 23, 2025):

I also tried using the GUI on Mac for download, there the issue is also appearing for all models. Download starts, works for a while and the stops

<!-- gh-comment-id:3435566833 --> @simonaden commented on GitHub (Oct 23, 2025): I also tried using the GUI on Mac for download, there the issue is also appearing for all models. Download starts, works for a while and the stops
GiteaMirror commented 2026-04-12 21:08:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 23, 2025):

Seems to be a server-side problem - I have tried downloading the model GGUF from multiple sites on different networks and they all stall. I'm doing the downloading with curl and wget so it's not an ollama client issue.

<!-- gh-comment-id:3435730861 --> @rick-github commented on GitHub (Oct 23, 2025): Seems to be a server-side problem - I have tried downloading the model GGUF from multiple sites on different networks and they all stall. I'm doing the downloading with curl and wget so it's not an ollama client issue.
GiteaMirror commented 2026-04-12 21:08:26 -05:00
Author
Owner
Copy Link

@jakeogrady commented on GitHub (Oct 23, 2025):

I am having an issue attempting to download with ollama pull llama3.1:latest. My speed is dropping to KBs

<!-- gh-comment-id:3435754470 --> @jakeogrady commented on GitHub (Oct 23, 2025): I am having an issue attempting to download with `ollama pull llama3.1:latest`. My speed is dropping to KBs
GiteaMirror commented 2026-04-12 21:08:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 23, 2025):

Seems to be a Cloudfare CDN issue. My downloads eventually completed, but very very slowly.

<!-- gh-comment-id:3435790271 --> @rick-github commented on GitHub (Oct 23, 2025): Seems to be a Cloudfare CDN issue. My downloads eventually completed, but very very slowly.
GiteaMirror commented 2026-04-12 21:08:29 -05:00
Author
Owner
Copy Link

@jakeogrady commented on GitHub (Oct 23, 2025):

Yes, I noticed that for the first 80-90% of the download it is performant, but the last 10% takes a long time and changes speed drastically.

<!-- gh-comment-id:3435798031 --> @jakeogrady commented on GitHub (Oct 23, 2025): Yes, I noticed that for the first 80-90% of the download it is performant, but the last 10% takes a long time and changes speed drastically.
GiteaMirror commented 2026-04-12 21:08:30 -05:00
Author
Owner
Copy Link

@sparkxdev commented on GitHub (Oct 23, 2025):

i can confirm. the last 10% dripple in kb/s and take several times longer than the first 90%.

<!-- gh-comment-id:3435916491 --> @sparkxdev commented on GitHub (Oct 23, 2025): i can confirm. the last 10% dripple in kb/s and take several times longer than the first 90%.
GiteaMirror commented 2026-04-12 21:08:31 -05:00
Author
Owner
Copy Link

@simonaden commented on GitHub (Oct 23, 2025):

yea on my machines the download eventually finish aswell, just takes a little while when the Mb/s drop to Kb/s

<!-- gh-comment-id:3436116441 --> @simonaden commented on GitHub (Oct 23, 2025): yea on my machines the download eventually finish aswell, just takes a little while when the Mb/s drop to Kb/s
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#8454
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?