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 #3875] Error: pull model manifest: 401 #64439

New Issue
Closed
opened 2026-05-03 17:38:45 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-05-03 17:38:45 -05:00
Owner
Copy Link

Originally created by @seedpower on GitHub (Apr 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3875

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

OS: Ubuntu 22.04 server
ollama version: 0.1.32

Using official bash script to install it or docker method to run it, both can't pull any model and get same next error:

# ollama run llama3
pulling manifest 
Error: pull model manifest: 401

In same network environment, my macOS system can pull llama3 model.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.32

Originally created by @seedpower on GitHub (Apr 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3875 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? OS: Ubuntu 22.04 server ollama version: 0.1.32 Using official bash script to install it or docker method to run it, both can't pull any model and get same next error: ``` # ollama run llama3 pulling manifest Error: pull model manifest: 401 ``` In same network environment, my macOS system can pull llama3 model. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-05-03 17:38:45 -05:00
GiteaMirror commented 2026-05-03 17:38:54 -05:00
Author
Owner
Copy Link

@sahilchauhan123 commented on GitHub (Apr 26, 2024):

Same my issue but my terminal no host here

<!-- gh-comment-id:2078650610 --> @sahilchauhan123 commented on GitHub (Apr 26, 2024): Same my issue but my terminal no host here
GiteaMirror commented 2026-05-03 17:38:55 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 1, 2024):

Can you share the server log? This sounds like a potential firewall/proxy issue.

<!-- gh-comment-id:2089236508 --> @dhiltgen commented on GitHub (May 1, 2024): Can you share the server log? This sounds like a potential firewall/proxy issue.
GiteaMirror commented 2026-05-03 17:38:58 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 21, 2024):

Please make sure to update to the latest version, and if you're still having problems, share the server log and I'll reopen.

<!-- gh-comment-id:2123132407 --> @dhiltgen commented on GitHub (May 21, 2024): Please make sure to update to the latest version, and if you're still having problems, share the server log and I'll reopen.
GiteaMirror commented 2026-05-03 17:39:00 -05:00
Author
Owner
Copy Link

@skye-code commented on GitHub (Jun 13, 2024):

Hello, i have the same issue with Ollama v0.1.43 on win11 locally, my models work fine but i can't pull or run any new models I get=> pulling manifest
Error: pull model manifest: 401

I tried reinstalling, or install a previous version, it didn't help. I also have openwebui with docker on the pc, it works fine as well, but i can't add any new model. I don't understand what happened from one day to another....
I tried to disable my firewall and windows defender and try again but it didn't change anything.

server.log

<!-- gh-comment-id:2165455546 --> @skye-code commented on GitHub (Jun 13, 2024): Hello, i have the same issue with Ollama v0.1.43 on win11 locally, my models work fine but i can't pull or run any new models I get=> pulling manifest Error: pull model manifest: 401 I tried reinstalling, or install a previous version, it didn't help. I also have openwebui with docker on the pc, it works fine as well, but i can't add any new model. I don't understand what happened from one day to another.... I tried to disable my firewall and windows defender and try again but it didn't change anything. [server.log](https://github.com/user-attachments/files/15818762/server.log)
GiteaMirror commented 2026-05-03 17:39:04 -05:00
Author
Owner
Copy Link

@simschmid commented on GitHub (Jun 13, 2024):

same here on win11. Neither the docker- nor the windows-version is able to pull models.
After checking the system clock it worked for me 🤦

<!-- gh-comment-id:2166771577 --> @simschmid commented on GitHub (Jun 13, 2024): ~~same here on win11. Neither the docker- nor the windows-version is able to pull models.~~ After checking the system clock it worked for me 🤦
GiteaMirror commented 2026-05-03 17:39:06 -05:00
Author
Owner
Copy Link

@newskyforest commented on GitHub (Jun 20, 2024):

sure, after using ntpdate tool, system clock synchronization. The problem was solved.

<!-- gh-comment-id:2180058430 --> @newskyforest commented on GitHub (Jun 20, 2024): sure, after using ntpdate tool, system clock synchronization. The problem was solved.
GiteaMirror commented 2026-05-03 17:39:07 -05:00
Author
Owner
Copy Link

@mrkanet commented on GitHub (Jul 24, 2024):

Same problem and worked with the solution: "After checking the system clock it worked for me 🤦"

<!-- gh-comment-id:2248589491 --> @mrkanet commented on GitHub (Jul 24, 2024): Same problem and worked with the solution: "After checking the system clock it worked for me 🤦"
GiteaMirror commented 2026-05-03 17:39:10 -05:00
Author
Owner
Copy Link

@greencounlimited commented on GitHub (Oct 11, 2024):

I just turned my Firewall off and it worked!!! But I suggest to re-enable it after installing because ollama still works after that.

<!-- gh-comment-id:2406619587 --> @greencounlimited commented on GitHub (Oct 11, 2024): I just turned my Firewall off and it worked!!! But I suggest to re-enable it after installing because ollama still works after that.
GiteaMirror commented 2026-05-03 17:39:12 -05:00
Author
Owner
Copy Link

@joengelh commented on GitHub (Apr 22, 2025):

same here on win11. Neither the docker- nor the windows-version is able to pull models. After checking the system clock it worked for me 🤦

How did you check the system clock?

<!-- gh-comment-id:2821716357 --> @joengelh commented on GitHub (Apr 22, 2025): > ~same here on win11. Neither the docker- nor the windows-version is able to pull models.~ After checking the system clock it worked for me 🤦 How did you check the system clock?
GiteaMirror commented 2026-05-03 17:39:14 -05:00
Author
Owner
Copy Link

@rahmat-ullah commented on GitHub (Jun 26, 2025):

I had the same issue; my issue was fixed after updating the date and time.

<!-- gh-comment-id:3008169493 --> @rahmat-ullah commented on GitHub (Jun 26, 2025): I had the same issue; my issue was fixed after updating the date and time.
GiteaMirror commented 2026-05-03 17:39:15 -05:00
Author
Owner
Copy Link

@Oak-AN commented on GitHub (Aug 10, 2025):

after getting Error: pull model manifest: 401 I ran these commands to sync the clock and everything worked

timedatectl status
sudo timedatectl set-ntp true
sudo systemctl restart systemd-timesyncd
<!-- gh-comment-id:3172865671 --> @Oak-AN commented on GitHub (Aug 10, 2025): after getting `Error: pull model manifest: 401` I ran these commands to sync the clock and everything worked ```sh timedatectl status sudo timedatectl set-ntp true sudo systemctl restart systemd-timesyncd ```
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#64439
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?