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 #8501] ollama run llama3-70b pulling very slow #67535

New Issue
Closed
opened 2026-05-04 10:42:07 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 10:42:07 -05:00
Owner
Copy Link

Originally created by @kowshik1234 on GitHub (Jan 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8501

What is the issue?

Hi,

I just downloaded ollama and tried to run the command ollama pull llama3:70b-instruct-q2_K, the download starts with good speed and exactly after 4-5 seconds speeds drop drastically to 165kbps and lower. Most of the times it stays at 0B, I tried this with both my home network and office networks same results.

Sometimes download itself fails with the error message

Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/a0/a09affdc2dffd0db03e7f0d1344c374d85add72ea4c715aa69b7b427f03d35d3/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250120%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250120T122125Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=16cdd624dc40ad8b40c4ca96bca353dfcfd259afe1ba911684b37fd44bb12541": net/http: TLS handshake timeout
Please help me !

OS

Linux

GPU

AMD

CPU

Intel

Ollama version

ollama version is 0.5.7

Originally created by @kowshik1234 on GitHub (Jan 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8501 ### What is the issue? Hi, I just downloaded ollama and tried to run the command ` ollama pull llama3:70b-instruct-q2_K`, the download starts with good speed and exactly after 4-5 seconds speeds drop drastically to 165kbps and lower. Most of the times it stays at 0B, I tried this with both my home network and office networks same results. Sometimes download itself fails with the error message `Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/a0/a09affdc2dffd0db03e7f0d1344c374d85add72ea4c715aa69b7b427f03d35d3/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250120%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250120T122125Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=16cdd624dc40ad8b40c4ca96bca353dfcfd259afe1ba911684b37fd44bb12541": net/http: TLS handshake timeout ` Please help me ! ### OS Linux ### GPU AMD ### CPU Intel ### Ollama version ollama version is 0.5.7
GiteaMirror added the bug label 2026-05-04 10:42:08 -05:00
GiteaMirror commented 2026-05-04 10:42:14 -05:00
Author
Owner
Copy Link

@kowshik1234 commented on GitHub (Jan 21, 2025):

My bad, I am able to pull it properly now, not sure what happened with my setup. Sorry for this :)

<!-- gh-comment-id:2605871922 --> @kowshik1234 commented on GitHub (Jan 21, 2025): My bad, I am able to pull it properly now, not sure what happened with my setup. Sorry for this :)
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#67535
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?