github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #850] Slow download speed #62444

New Issue
Closed
opened 2026-05-03 08:59:48 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 08:59:48 -05:00
Owner
Copy Link

Originally created by @youssef02 on GitHub (Oct 20, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/850

Is there. A possible way to have manual installation, because I want to download the model from a fast proxy or something similar, the speed for. Mistral is 160 kbit/s, and 4 GB is it hosted on a different server or is it possible to download using a torrent or something that don't limit my download speed, I have WARP to bypass Türkiye IP ban, but the speed is still causing me headache,

can someone tell me what are my options. Here. Thanks in advance.

Originally created by @youssef02 on GitHub (Oct 20, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/850 Is there. A possible way to have manual installation, because I want to download the model from a fast proxy or something similar, the speed for. Mistral is 160 kbit/s, and 4 GB is it hosted on a different server or is it possible to download using a torrent or something that don't limit my download speed, I have WARP to bypass Türkiye IP ban, but the speed is still causing me headache, can someone tell me what are my options. Here. Thanks in advance.
GiteaMirror commented 2026-05-03 08:59:49 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Oct 20, 2023):

@youssef02 Ollama library shouldn't limit the download speed. It uses Cloudflare to serve the models at their edge.

Is there a VPN or some kind of tunnel that you are using?

<!-- gh-comment-id:1773423599 --> @mchiang0610 commented on GitHub (Oct 20, 2023): @youssef02 Ollama library shouldn't limit the download speed. It uses Cloudflare to serve the models at their edge. Is there a VPN or some kind of tunnel that you are using?
GiteaMirror commented 2026-05-03 08:59:50 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Oct 26, 2023):

Hi @youssef02 just wanted to follow up on this to see if it's something we can help with

<!-- gh-comment-id:1780226016 --> @mchiang0610 commented on GitHub (Oct 26, 2023): Hi @youssef02 just wanted to follow up on this to see if it's something we can help with
GiteaMirror commented 2026-05-03 08:59:51 -05:00
Author
Owner
Copy Link

@youssef02 commented on GitHub (Oct 26, 2023):

Yeah idk either but i travelled outside of istanbul and it was downloading
normaly, when I was inside istanbul tried different wifi, like uni and
coffee shops but still had that problem, but it was fast when I downloaded
it yesterday

So i think the problem is solved

Thanks for keeping with this problem. XD

On Thu, Oct 26, 2023, 03:14 Michael @.***> wrote:

Hi @youssef02 https://github.com/youssef02 just wanted to follow up on
this to see if it's something we can help with

—
Reply to this email directly, view it on GitHub
https://github.com/jmorganca/ollama/issues/850#issuecomment-1780226016,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AGJIWYV45PHGDBITIBNIOPDYBGTNLAVCNFSM6AAAAAA6JCCJHWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGIZDMMBRGY
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:1780423655 --> @youssef02 commented on GitHub (Oct 26, 2023): Yeah idk either but i travelled outside of istanbul and it was downloading normaly, when I was inside istanbul tried different wifi, like uni and coffee shops but still had that problem, but it was fast when I downloaded it yesterday So i think the problem is solved Thanks for keeping with this problem. XD On Thu, Oct 26, 2023, 03:14 Michael ***@***.***> wrote: > Hi @youssef02 <https://github.com/youssef02> just wanted to follow up on > this to see if it's something we can help with > > — > Reply to this email directly, view it on GitHub > <https://github.com/jmorganca/ollama/issues/850#issuecomment-1780226016>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AGJIWYV45PHGDBITIBNIOPDYBGTNLAVCNFSM6AAAAAA6JCCJHWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBQGIZDMMBRGY> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
GiteaMirror commented 2026-05-03 08:59:52 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 26, 2023):

We don't currently use a CDN for the models, but we just did a number of changes to the client which should improve pulling by trying to snag more chunks of the model at once.

I'll close the issue for now, but @youssef02 feel free to re-open or create a new issue if you're still having performance issues.

<!-- gh-comment-id:1781832616 --> @pdevine commented on GitHub (Oct 26, 2023): We don't currently use a CDN for the models, but we just did a number of changes to the client which should improve pulling by trying to snag more chunks of the model at once. I'll close the issue for now, but @youssef02 feel free to re-open or create a new issue if you're still having performance issues.
GiteaMirror commented 2026-05-03 08:59:53 -05:00
Author
Owner
Copy Link

@youssef02 commented on GitHub (Oct 26, 2023):

All good, I think that solved the problem.

Thanks for upgrade.

On Thu, Oct 26, 2023, 23:13 Patrick Devine @.***> wrote:

We don't currently use a CDN for the models, but we just did a number of
changes to the client which should improve pulling by trying to snag more
chunks of the model at once.

I'll close the issue for now, but @youssef02
https://github.com/youssef02 feel free to re-open or create a new issue
if you're still having performance issues.

—
Reply to this email directly, view it on GitHub
https://github.com/jmorganca/ollama/issues/850#issuecomment-1781832616,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AGJIWYVM4M43323K7LQOHMLYBLAAJAVCNFSM6AAAAAA6JCCJHWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBRHAZTENRRGY
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:1781835273 --> @youssef02 commented on GitHub (Oct 26, 2023): All good, I think that solved the problem. Thanks for upgrade. On Thu, Oct 26, 2023, 23:13 Patrick Devine ***@***.***> wrote: > We don't currently use a CDN for the models, but we just did a number of > changes to the client which should improve pulling by trying to snag more > chunks of the model at once. > > I'll close the issue for now, but @youssef02 > <https://github.com/youssef02> feel free to re-open or create a new issue > if you're still having performance issues. > > — > Reply to this email directly, view it on GitHub > <https://github.com/jmorganca/ollama/issues/850#issuecomment-1781832616>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AGJIWYVM4M43323K7LQOHMLYBLAAJAVCNFSM6AAAAAA6JCCJHWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTOOBRHAZTENRRGY> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
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#62444
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?