github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3816] i/o timeout when running ollama pull #64397

New Issue
Closed
opened 2026-05-03 17:28:02 -05:00 by GiteaMirror · 18 comments
GiteaMirror commented 2026-05-03 17:28:02 -05:00
Owner
Copy Link

Originally created by @pitilessj on GitHub (Apr 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3816

What is the issue?

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/8b": dial tcp 104.21.75.227:443: i/o timeout

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.1.32

Originally created by @pitilessj on GitHub (Apr 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3816 ### What is the issue? pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/8b": dial tcp 104.21.75.227:443: i/o timeout ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.1.32
GiteaMirror added the networkingbug labels 2026-05-03 17:28:02 -05:00
GiteaMirror commented 2026-05-03 17:28:04 -05:00
Author
Owner
Copy Link

@luzik commented on GitHub (Apr 22, 2024):

It's looking like network problem

<!-- gh-comment-id:2069005397 --> @luzik commented on GitHub (Apr 22, 2024): It's looking like network problem
GiteaMirror commented 2026-05-03 17:28:05 -05:00
Author
Owner
Copy Link

@LitghtCoder commented on GitHub (Apr 23, 2024):

INFO source=images.go:1147 msg="request failed: Get "https://registry.ollama.ai/v2/library/llama3/manifests/latest": dial tcp 172.67.182.229:443: i/o timeout"
I encountered the same issue.

<!-- gh-comment-id:2071890375 --> @LitghtCoder commented on GitHub (Apr 23, 2024): INFO source=images.go:1147 msg="request failed: Get \"https://registry.ollama.ai/v2/library/llama3/manifests/latest\": dial tcp 172.67.182.229:443: i/o timeout" I encountered the same issue.
GiteaMirror commented 2026-05-03 17:28:05 -05:00
Author
Owner
Copy Link

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

Can you ping registry.ollama.ai from the system where you're running ollama? If that works, can you try to curl https://registry.ollama.ai/v2/_catalog (will take a while, but should produce a list of some of the models)

<!-- gh-comment-id:2089297093 --> @dhiltgen commented on GitHub (May 1, 2024): Can you ping registry.ollama.ai from the system where you're running ollama? If that works, can you try to `curl https://registry.ollama.ai/v2/_catalog` (will take a while, but should produce a list of some of the models)
GiteaMirror commented 2026-05-03 17:28:06 -05:00
Author
Owner
Copy Link

@loFei commented on GitHub (May 2, 2024):

I also encountered this problem. When I use curl to access "https://registry.ollama.ai/v2/library/llama3/manifests/latest", the return result is like this:

{"errors":[{"code":"MANIFEST_INVALID","message":"manifest invalid","detail":{}}]}

<!-- gh-comment-id:2091210068 --> @loFei commented on GitHub (May 2, 2024): I also encountered this problem. When I use curl to access "https://registry.ollama.ai/v2/library/llama3/manifests/latest", the return result is like this: {"errors":[{"code":"MANIFEST_INVALID","message":"manifest invalid","detail":{}}]}
GiteaMirror commented 2026-05-03 17:28:07 -05:00
Author
Owner
Copy Link

@bk8702 commented on GitHub (May 18, 2024):

curl -s https://registry.ollama.ai/v2/_catalog | jq '.repositories[] | select(contains("llama3"))'
"549165334/llama3-chinese"
"abdulm3003/llama3"
"abrahammg/llama3-gl-chat"
"adrienbrault/nous-hermes2pro-llama3-8b-test"
"adrienbrault/nous-hermes2pro-llama3-8b"
"adrienbrault/nous-hermes2theta-llama3-8b"
"adsfaaron/llama3-taide-lx-8b-chat-alpha"
"aibangjuxin/llama3"
"amithmkini/llama3-64k"
"anton96vice/av-tg-llama3-instr-4q"

There is no "library/llama3" repository in the registry!

<!-- gh-comment-id:2118804383 --> @bk8702 commented on GitHub (May 18, 2024): ```bash curl -s https://registry.ollama.ai/v2/_catalog | jq '.repositories[] | select(contains("llama3"))' "549165334/llama3-chinese" "abdulm3003/llama3" "abrahammg/llama3-gl-chat" "adrienbrault/nous-hermes2pro-llama3-8b-test" "adrienbrault/nous-hermes2pro-llama3-8b" "adrienbrault/nous-hermes2theta-llama3-8b" "adsfaaron/llama3-taide-lx-8b-chat-alpha" "aibangjuxin/llama3" "amithmkini/llama3-64k" "anton96vice/av-tg-llama3-instr-4q" ``` There is no "library/llama3" repository in the registry!
GiteaMirror commented 2026-05-03 17:28:07 -05:00
Author
Owner
Copy Link

@AmarkanthJinna commented on GitHub (May 29, 2024):

Hi, Please help me.

ollama run llama3

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/latest": dial tcp 104.21.75.227:443: I/o timed out

I'm behind corporate proxy

http://proxy.ebiz.corporate.com:80

Is this proxy issue? How can I add proxy here on my linux machine

<!-- gh-comment-id:2138154593 --> @AmarkanthJinna commented on GitHub (May 29, 2024): Hi, Please help me. ollama run llama3 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3/manifests/latest": dial tcp 104.21.75.227:443: I/o timed out I'm behind corporate proxy [http://proxy.ebiz.corporate.com:80](http://proxy.ebiz.corporate.com/) Is this proxy issue? How can I add proxy here on my linux machine
GiteaMirror commented 2026-05-03 17:28:08 -05:00
Author
Owner
Copy Link

@ccxuy commented on GitHub (Aug 21, 2024):

@AmarkanthJinna
Same here:

ollama run llama3.1
pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.1/manifests/latest": dial tcp 172.67.182.229:443: i/o timeout

                                                                                                                                                                     
 1 > curl -s "https://registry.ollama.ai/v2/library/llama3.1/manifests/latest"


The model you are attempting to pull requires a newer version of Ollama.

Please download the latest version at:

        https://ollama.com/download
<!-- gh-comment-id:2301635959 --> @ccxuy commented on GitHub (Aug 21, 2024): @AmarkanthJinna Same here: ``` ollama run llama3.1 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama3.1/manifests/latest": dial tcp 172.67.182.229:443: i/o timeout 1 > curl -s "https://registry.ollama.ai/v2/library/llama3.1/manifests/latest" The model you are attempting to pull requires a newer version of Ollama. Please download the latest version at: https://ollama.com/download ```
GiteaMirror commented 2026-05-03 17:28:08 -05:00
Author
Owner
Copy Link

@gmsurendra commented on GitHub (Aug 28, 2024):

I am having the same issue, I am able to do the curl for the URL.
but ollama is erroring with time out error.

OS: Windows

CURL successful


C:\Users\XXXXXX>curl -s https://registry.ollama.ai/v2/library/phi3/manifests/latest
{"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"digest":"sha256:23291dc44752bac878bf46ab0f2b8daf75c710060f80f1a351151c7be2f5ee0f","mediaType":"application/vnd.docker.container.image.v1+json","size":483},"layers":[{"digest":"sha256:633fc5be925f9a484b61d6f9b9a78021eeb462100bd557309f01ba84cac26adf","mediaType":"application/vnd.ollama.image.model","size":2176177120},{"digest":"sha256:fa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d","mediaType":"application/vnd.ollama.image.license","size":1084},{"digest":"sha256:542b217f179c7825eeb5bca3c77d2b75ed05bafbd3451d9188891a60a85337c6","mediaType":"application/vnd.ollama.image.template","size":148},{"digest":"sha256:8dde1baf1db03d318a2ab076ae363318357dff487bdd8c1703a29886611e581f","mediaType":"application/vnd.ollama.image.params","size":78}]}

Timeout from Ollama

C:\Users\XXXX>ollama pull phi3
pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/phi3/manifests/latest": dial tcp 172.67.182.229:443: i/o timeout
<!-- gh-comment-id:2315978960 --> @gmsurendra commented on GitHub (Aug 28, 2024): I am having the same issue, I am able to do the curl for the URL. but ollama is erroring with time out error. OS: Windows **CURL successful** ``` C:\Users\XXXXXX>curl -s https://registry.ollama.ai/v2/library/phi3/manifests/latest {"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"digest":"sha256:23291dc44752bac878bf46ab0f2b8daf75c710060f80f1a351151c7be2f5ee0f","mediaType":"application/vnd.docker.container.image.v1+json","size":483},"layers":[{"digest":"sha256:633fc5be925f9a484b61d6f9b9a78021eeb462100bd557309f01ba84cac26adf","mediaType":"application/vnd.ollama.image.model","size":2176177120},{"digest":"sha256:fa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d","mediaType":"application/vnd.ollama.image.license","size":1084},{"digest":"sha256:542b217f179c7825eeb5bca3c77d2b75ed05bafbd3451d9188891a60a85337c6","mediaType":"application/vnd.ollama.image.template","size":148},{"digest":"sha256:8dde1baf1db03d318a2ab076ae363318357dff487bdd8c1703a29886611e581f","mediaType":"application/vnd.ollama.image.params","size":78}]} ``` **Timeout from Ollama** ``` C:\Users\XXXX>ollama pull phi3 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/phi3/manifests/latest": dial tcp 172.67.182.229:443: i/o timeout ```
GiteaMirror commented 2026-05-03 17:28:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 3, 2024):

@gmsurendra that might be a proxy problem. If you have a proxy in your environment, can you try these instructions https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy

<!-- gh-comment-id:2327133573 --> @dhiltgen commented on GitHub (Sep 3, 2024): @gmsurendra that might be a proxy problem. If you have a proxy in your environment, can you try these instructions https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy
GiteaMirror commented 2026-05-03 17:28:09 -05:00
Author
Owner
Copy Link

@saiprem-A commented on GitHub (Sep 16, 2024):

Follow these steps it worked for me:
step 1: Stop ollama service

sudo systemctl ollama.service

step 2: launch ollama separate terminal

ollama serve

step3: pull the model
ollama pull llama3.1 will work now

<!-- gh-comment-id:2352140016 --> @saiprem-A commented on GitHub (Sep 16, 2024): Follow these steps it worked for me: step 1: Stop ollama service sudo systemctl ollama.service step 2: launch ollama separate terminal ollama serve step3: pull the model ollama pull llama3.1 will work now
GiteaMirror commented 2026-05-03 17:28:09 -05:00
Author
Owner
Copy Link

@InfernalAzazel commented on GitHub (Oct 14, 2024):

Set proxy

image

$ curl -s https://registry.ollama.ai/v2/library/phi3/manifests/latest
{"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"digest":"sha256:23291dc44752bac878bf46ab0f2b8daf75c710060f80f1a351151c7be2f5ee0f","mediaType":"application/vnd.docker.container.image.v1+json","size":483},"layers":[{"digest":"sha256:633fc5be925f9a484b61d6f9b9a78021eeb462100bd557309f01ba84cac26adf","mediaType":"application/vnd.ollama.image.model","size":2176177120},{"digest":"sha256:fa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d","mediaType":"application/vnd.ollama.image.license","size":1084},{"digest":"sha256:542b217f179c7825eeb5bca3c77d2b75ed05bafbd3451d9188891a60a85337c6","mediaType":"application/vnd.ollama.image.template","size":148},{"digest":"sha256:8dde1baf1db03d318a2ab076ae363318357dff487bdd8c1703a29886611e581f","mediaType":"application/vnd.ollama.image.params","size":78}]}

error

ollama run qwen2.5
pulling manifest 
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2.5/manifests/latest": proxyconnect tcp: dial tcp 127.0.0.1:7890: connect: connection refused
<!-- gh-comment-id:2409915156 --> @InfernalAzazel commented on GitHub (Oct 14, 2024): Set proxy ![image](https://github.com/user-attachments/assets/dd2d73a7-d926-4ac2-88ac-2fe47d2b6ec1) ```shell $ curl -s https://registry.ollama.ai/v2/library/phi3/manifests/latest {"schemaVersion":2,"mediaType":"application/vnd.docker.distribution.manifest.v2+json","config":{"digest":"sha256:23291dc44752bac878bf46ab0f2b8daf75c710060f80f1a351151c7be2f5ee0f","mediaType":"application/vnd.docker.container.image.v1+json","size":483},"layers":[{"digest":"sha256:633fc5be925f9a484b61d6f9b9a78021eeb462100bd557309f01ba84cac26adf","mediaType":"application/vnd.ollama.image.model","size":2176177120},{"digest":"sha256:fa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d","mediaType":"application/vnd.ollama.image.license","size":1084},{"digest":"sha256:542b217f179c7825eeb5bca3c77d2b75ed05bafbd3451d9188891a60a85337c6","mediaType":"application/vnd.ollama.image.template","size":148},{"digest":"sha256:8dde1baf1db03d318a2ab076ae363318357dff487bdd8c1703a29886611e581f","mediaType":"application/vnd.ollama.image.params","size":78}]} ``` error ```shell ollama run qwen2.5 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2.5/manifests/latest": proxyconnect tcp: dial tcp 127.0.0.1:7890: connect: connection refused ```
GiteaMirror commented 2026-05-03 17:28:10 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 14, 2024):

@InfernalAzazel currently Ollama does not read the system proxy setting and requires an environment variable for the server. If you set the variables it should work.

<!-- gh-comment-id:2411646598 --> @dhiltgen commented on GitHub (Oct 14, 2024): @InfernalAzazel currently Ollama does not read the [system proxy setting](https://github.com/ollama/ollama/issues/5354) and requires an [environment variable for the server](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy). If you set the variables it should work.
GiteaMirror commented 2026-05-03 17:28:10 -05:00
Author
Owner
Copy Link

@InfernalAzazel commented on GitHub (Oct 15, 2024):

@InfernalAzazel currently Ollama does not read the system proxy setting and requires an environment variable for the server. If you set the variables it should work.

This variable exists

image

Is there a way to configure the model manually? For example, should I download qwen2.5 first and then configure ollama?

<!-- gh-comment-id:2412942104 --> @InfernalAzazel commented on GitHub (Oct 15, 2024): > @InfernalAzazel currently Ollama does not read the [system proxy setting](https://github.com/ollama/ollama/issues/5354) and requires an [environment variable for the server](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy). If you set the variables it should work. This variable exists ![image](https://github.com/user-attachments/assets/bc23f752-3795-4277-b5db-9bb847d10d5d) Is there a way to configure the model manually? For example, should I download qwen2.5 first and then configure ollama?
GiteaMirror commented 2026-05-03 17:28:11 -05:00
Author
Owner
Copy Link

@InfernalAzazel commented on GitHub (Oct 15, 2024):

@InfernalAzazel currently Ollama does not read the system proxy setting and requires an environment variable for the server. If you set the variables it should work.

I solved it via docker proxy

docker run -d -e HTTPS_PROXY=https://my.proxy.example.com -p 11434:11434 ollama-with-ca

How can I cleanly uninstall ollama that I installed locally through the shell?

<!-- gh-comment-id:2412987776 --> @InfernalAzazel commented on GitHub (Oct 15, 2024): > @InfernalAzazel currently Ollama does not read the [system proxy setting](https://github.com/ollama/ollama/issues/5354) and requires an [environment variable for the server](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy). If you set the variables it should work. I solved it via docker proxy ```shell docker run -d -e HTTPS_PROXY=https://my.proxy.example.com -p 11434:11434 ollama-with-ca ``` How can I cleanly uninstall ollama that I installed locally through the shell?
GiteaMirror commented 2026-05-03 17:28:11 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 15, 2024):

@InfernalAzazel uninstall instructions are located here - https://github.com/ollama/ollama/blob/main/docs/linux.md#uninstall

Getting proxy configuration right can be tricky. Glad to hear you got it working.

<!-- gh-comment-id:2414794838 --> @dhiltgen commented on GitHub (Oct 15, 2024): @InfernalAzazel uninstall instructions are located here - https://github.com/ollama/ollama/blob/main/docs/linux.md#uninstall Getting proxy configuration right can be tricky. Glad to hear you got it working.
GiteaMirror commented 2026-05-03 17:28:12 -05:00
Author
Owner
Copy Link

@Noarchees commented on GitHub (Feb 17, 2025):

I resolved if add paramaters bellow to system edit ollama.

[Service]
Environment="HTTP_PROXY=http://<proxyserver>:<port>" 
Environment="HTTPS_PROXY=http://<proxyserver>:<port>"

ollama restart

$ systemctl daemon-reload
$ systemctl restart ollama
<!-- gh-comment-id:2661711602 --> @Noarchees commented on GitHub (Feb 17, 2025): I resolved if add paramaters bellow to `system edit ollama`. ``` [Service] Environment="HTTP_PROXY=http://<proxyserver>:<port>" Environment="HTTPS_PROXY=http://<proxyserver>:<port>" ``` ollama restart ``` $ systemctl daemon-reload $ systemctl restart ollama ```
GiteaMirror commented 2026-05-03 17:28:13 -05:00
Author
Owner
Copy Link

@yueyunyue commented on GitHub (Feb 26, 2025):

I had the same issue, and I solved it. When Ollama starts, it gets the environment variable "HTTP_PROXY". If you set this environment variable after Ollama starts, it retrieves nothing. So, you must set the environment variable before Ollama starts. If Ollama is already started, set the environment variable and then restart Ollama.

<!-- gh-comment-id:2684111937 --> @yueyunyue commented on GitHub (Feb 26, 2025): I had the same issue, and I solved it. When Ollama starts, it gets the environment variable "HTTP_PROXY". If you set this environment variable after Ollama starts, it retrieves nothing. So, you must set the environment variable before Ollama starts. If Ollama is already started, set the environment variable and then restart Ollama.
GiteaMirror commented 2026-05-03 17:28:13 -05:00
Author
Owner
Copy Link

@BombFoolGranny commented on GitHub (Mar 8, 2026):

For those of you using docker, try getting inside the container: docker exec -it $OLLAMA_CONTAINER_ID /bin/bash
And then restart ollama there by killing its process. I did it once and got it all fixed

<!-- gh-comment-id:4018905290 --> @BombFoolGranny commented on GitHub (Mar 8, 2026): For those of you using docker, try getting inside the container: `docker exec -it $OLLAMA_CONTAINER_ID /bin/bash` And then restart ollama there by killing its process. I did it once and got it all fixed
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 networking
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#64397
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?