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 #6334] ./ollama-linux-amd64 pull llama3.1:405b the rate very slow, only several Kb/s #66011

New Issue
Closed
opened 2026-05-03 23:35:58 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 23:35:58 -05:00
Owner
Copy Link

Originally created by @EGOIST5 on GitHub (Aug 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6334

What is the issue?

Before the version of ollama-linux-amd64 update, I could pull the models normally. But once I updated the new version of ollama-linux-amd64, pulling the models fails frequently.
Command: ./ollama-linux-amd64 pull llama3.1:405b
sometimes it will print the following error:
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.1/manifests/405b": net/http: TLS handshake timeout
And sometimes I could pull the request, but the download rate is nearly zero
And the server will report:
time=2024-08-13T05:24:21.850-04:00 level=INFO source=download.go:370 msg="939fd971f038 part 43 stalled; retrying. If this persists, press ctrl-c to exit
, then 'ollama pull' to find a faster connection."
time=2024-08-13T05:24:21.881-04:00 level=INFO source=download.go:291 msg="939fd971f038 part 10 attempt 1 failed: Get "https://dd20bb891979d25aebc8bec07
b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/93/939fd971f03801a9447af720a78d1fc00833cadf05252b4fc871bfb70eafdda6/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240813%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240813T092341Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=e9309a6a23b298d8993983a4c47f04311f5dfe41037808a421ba240c37b9f0af": net/http: TLS handshake timeout, retrying in 2s"

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @EGOIST5 on GitHub (Aug 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6334 ### What is the issue? Before the version of ollama-linux-amd64 update, I could pull the models normally. But once I updated the new version of ollama-linux-amd64, pulling the models fails frequently. Command: ./ollama-linux-amd64 pull llama3.1:405b sometimes it will print the following error: Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.1/manifests/405b": net/http: TLS handshake timeout And sometimes I could pull the request, but the download rate is nearly zero And the server will report: time=2024-08-13T05:24:21.850-04:00 level=INFO source=download.go:370 msg="939fd971f038 part 43 stalled; retrying. If this persists, press ctrl-c to exit , then 'ollama pull' to find a faster connection." time=2024-08-13T05:24:21.881-04:00 level=INFO source=download.go:291 msg="939fd971f038 part 10 attempt 1 failed: Get \"https://dd20bb891979d25aebc8bec07 b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/93/939fd971f03801a9447af720a78d1fc00833cadf05252b4fc871bfb70eafdda6/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240813%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240813T092341Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=e9309a6a23b298d8993983a4c47f04311f5dfe41037808a421ba240c37b9f0af\": net/http: TLS handshake timeout, retrying in 2s" ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-03 23:35:58 -05:00
GiteaMirror commented 2026-05-03 23:36:06 -05:00
Author
Owner
Copy Link

@rampageservices commented on GitHub (Aug 13, 2024):

Have you tried running speed tests separately to ensure it is not your connection?
https://www.speedtest.net/

I'm not saying it is 100% not a problem with Ollama but if you show that your connection fares well in speed tests while your having issues pulling it could lead to better knowledge that it is indeed an Ollama issue.

<!-- gh-comment-id:2286443979 --> @rampageservices commented on GitHub (Aug 13, 2024): Have you tried running speed tests separately to ensure it is not your connection? https://www.speedtest.net/ I'm not saying it is 100% not a problem with Ollama but if you show that your connection fares well in speed tests while your having issues pulling it could lead to better knowledge that it is indeed an Ollama issue.
GiteaMirror commented 2026-05-03 23:36:11 -05:00
Author
Owner
Copy Link

@EGOIST5 commented on GitHub (Aug 14, 2024):

Have you tried running speed tests separately to ensure it is not your connection? https://www.speedtest.net/

I'm not saying it is 100% not a problem with Ollama but if you show that your connection fares well in speed tests while your having issues pulling it could lead to better knowledge that it is indeed an Ollama issue.

Thank you a lot. Before I saw your reply, I can download normally again, maybe my bad network. Thank you

<!-- gh-comment-id:2287891546 --> @EGOIST5 commented on GitHub (Aug 14, 2024): > Have you tried running speed tests separately to ensure it is not your connection? https://www.speedtest.net/ > > I'm not saying it is 100% not a problem with Ollama but if you show that your connection fares well in speed tests while your having issues pulling it could lead to better knowledge that it is indeed an Ollama issue. Thank you a lot. Before I saw your reply, I can download normally again, maybe my bad network. Thank you
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#66011
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?