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 #6211] Error: max retries exceeded #29640

New Issue
Closed
opened 2026-04-22 08:41:18 -05:00 by GiteaMirror · 28 comments
GiteaMirror commented 2026-04-22 08:41:18 -05:00
Owner
Copy Link

Originally created by @igorschlum on GitHub (Aug 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6211

What is the issue?

I am in a place with a slow ADSL connection that works for loading pages and checking emails. However, I can't pull LLM models because it's regularly interrupted by an 'Error: max retries exceeded after about 2 or 3 minutes. If I use my phone with Share Connection, it works well in 5G. I don't think it's a new problem, as I don't often pull models from this location, but I remember that this issue was supposed to be fixed about a year ago.

(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 0% ▕ ▏ 240 MB/151 GB
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 0% ▕ ▏ 468 MB/151 GB
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 0% ▕ ▏ 709 MB/151 GB
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 1% ▕ ▏ 950 MB/151 GB
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 1% ▕ ▏ 1.1 GB/151 GB 316 KB/s 99h+
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 1% ▕ ▏ 1.4 GB/151 GB 1.3 MB/s 31h26m
Error: max retries exceeded: Get "91a950ecda/data": net/http: TLS handshake timeout
(base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K
pulling manifest
pulling 91a950ecda13... 1% ▕ ▏ 1.7 GB/151 GB
Error: max retries exceeded: Get "91a950ecda/data": read tcp 192.168.1.30:55654->104.18.9.90:443: read: connection reset by peer

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.3.4

Originally created by @igorschlum on GitHub (Aug 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6211 ### What is the issue? I am in a place with a slow ADSL connection that works for loading pages and checking emails. However, I can't pull LLM models because it's regularly interrupted by an 'Error: max retries exceeded after about 2 or 3 minutes. If I use my phone with Share Connection, it works well in 5G. I don't think it's a new problem, as I don't often pull models from this location, but I remember that this issue was supposed to be fixed about a year ago. (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 0% ▕ ▏ 240 MB/151 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T212828Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=b0480c0fd7b0c78a2204922fa1608e972c6438155b83ff03c7555a43fdc0e6b5": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 0% ▕ ▏ 468 MB/151 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T213331Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=12d37fed240dd1f741823322bb3718b46ca05e4f78eabaf4fc69054275592cd0": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 0% ▕ ▏ 709 MB/151 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T213930Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=2ba7b7e37ec8436dde00315d61e53fabc7bb784a4b2360a6c5f6b19e54e362e1": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 1% ▕ ▏ 950 MB/151 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T214526Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=e58417cf631b6443136f09b1dc99c131059a7021b712ec938a6c523426e56801": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 1% ▕ ▏ 1.1 GB/151 GB 316 KB/s 99h+ Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T214937Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=d0551598d8332b8fa7680e42c0bbf2298d9ea0d78afeeb1042c681b7c4563b64": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 1% ▕ ▏ 1.4 GB/151 GB 1.3 MB/s 31h26m Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T215955Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=410db491fc93079799905b740c91755269e7daf54433e3be6ae6a3e57f338209": net/http: TLS handshake timeout (base) igor@Mac-Studio-192 ~ % ollama pull llama3.1:405b-instruct-q2_K pulling manifest pulling 91a950ecda13... 1% ▕ ▏ 1.7 GB/151 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/91/91a950ecda13411e7b54f0df08b965a4ff2d38738556e89fbbe06ab5ee1a8d18/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20240806%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20240806T222208Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=bc366a803f1e3a7a717b3fd2ab54d31e6804057a0e4d0c4c77f5324d83cec398": read tcp 192.168.1.30:55654->104.18.9.90:443: read: connection reset by peer ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.4
GiteaMirror added the bug label 2026-04-22 08:41:18 -05:00
GiteaMirror commented 2026-04-22 08:41:21 -05:00
Author
Owner
Copy Link

@dkgaraujo commented on GitHub (Aug 7, 2024):

I am facing the same problem with an ubuntu computer, for llama3.1. I haven't tried with other LLMs but the previous version worked fine in the same machine, same config with llama3:

(base) douglas@ubuntu:~$ ollama run llama3.1
pulling manifest 
pulling 4f6dc812262a...   0% ▕                                                                                                                                                                ▏  12 MB/4.7 GB                  
Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/4f/4f6dc812262ac5e1a74791c2a86310ebba1aa1804fa3cd1c216f5547a620d2f2/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%!F(MISSING)20240807%!F(MISSING)auto%!F(MISSING)s3%!F(MISSING)aws4_request&X-Amz-Date=20240807T171933Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=f5827dcdc260bbfff08f9d872ac5f2ed2b1049f7789c151b9802267049bcc08a": dial tcp [2606:4700::6812:95a]:443: i/o timeout
<!-- gh-comment-id:2274434770 --> @dkgaraujo commented on GitHub (Aug 7, 2024): I am facing the same problem with an ubuntu computer, for llama3.1. I haven't tried with other LLMs but the previous version worked fine in the same machine, same config with llama3: ``` (base) douglas@ubuntu:~$ ollama run llama3.1 pulling manifest pulling 4f6dc812262a... 0% ▕ ▏ 12 MB/4.7 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/4f/4f6dc812262ac5e1a74791c2a86310ebba1aa1804fa3cd1c216f5547a620d2f2/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%!F(MISSING)20240807%!F(MISSING)auto%!F(MISSING)s3%!F(MISSING)aws4_request&X-Amz-Date=20240807T171933Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=f5827dcdc260bbfff08f9d872ac5f2ed2b1049f7789c151b9802267049bcc08a": dial tcp [2606:4700::6812:95a]:443: i/o timeout ```
GiteaMirror commented 2026-04-22 08:41:22 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 8, 2024):

In fact, when I pull a small model, it works well. No problem pulling phi3:mini, but ollama pull llama3.1:405b-instruct-q2_K cannot pull more than 200MB without error.

igor@Mac-Studio-192 ~ % ollama run phi3:mini
pulling manifest
pulling 633fc5be925f... 100% ▕████████████████▏ 2.2 GB
pulling fa8235e5b48f... 100% ▕████████████████▏ 1.1 KB
pulling 542b217f179c... 100% ▕████████████████▏ 148 B
pulling 8dde1baf1db0... 100% ▕████████████████▏ 78 B
pulling 23291dc44752... 100% ▕████████████████▏ 483 B
verifying sha256 digest
writing manifest
removing any unused layers
success

Send a message (/? for help)

<!-- gh-comment-id:2276746777 --> @igorschlum commented on GitHub (Aug 8, 2024): In fact, when I pull a small model, it works well. No problem pulling phi3:mini, but ollama pull llama3.1:405b-instruct-q2_K cannot pull more than 200MB without error. igor@Mac-Studio-192 ~ % ollama run phi3:mini pulling manifest pulling 633fc5be925f... 100% ▕████████████████▏ 2.2 GB pulling fa8235e5b48f... 100% ▕████████████████▏ 1.1 KB pulling 542b217f179c... 100% ▕████████████████▏ 148 B pulling 8dde1baf1db0... 100% ▕████████████████▏ 78 B pulling 23291dc44752... 100% ▕████████████████▏ 483 B verifying sha256 digest writing manifest removing any unused layers success >>> Send a message (/? for help)
GiteaMirror commented 2026-04-22 08:41:22 -05:00
Author
Owner
Copy Link

@rampageservices commented on GitHub (Aug 10, 2024):

People will keep running into this issue and more and more tickets will be created unless the project maintainers help to make the model downloader more robust by pulling this pending PR as a step in the right direction.

https://github.com/ollama/ollama/pull/4625

<!-- gh-comment-id:2281575113 --> @rampageservices commented on GitHub (Aug 10, 2024): People will keep running into this issue and more and more tickets will be created unless the project maintainers help to make the model downloader more robust by pulling this pending PR as a step in the right direction. https://github.com/ollama/ollama/pull/4625
GiteaMirror commented 2026-04-22 08:41:24 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 11, 2024):

Closing for https://github.com/ollama/ollama/issues/2006

<!-- gh-comment-id:2282919175 --> @igorschlum commented on GitHub (Aug 11, 2024): Closing for https://github.com/ollama/ollama/issues/2006
GiteaMirror commented 2026-04-22 08:41:25 -05:00
Author
Owner
Copy Link

@ziyouzhea commented on GitHub (Sep 19, 2024):

how to solve this problems?I met this error now.

<!-- gh-comment-id:2360095152 --> @ziyouzhea commented on GitHub (Sep 19, 2024): how to solve this problems?I met this error now.
GiteaMirror commented 2026-04-22 08:41:26 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Sep 19, 2024):

@liuwq999 It's a matter of the number of simultaneous threads used to pull a model. It was set too high, and although it was lowered, it still wasn't enough. This issue is now closed, and the discussion has moved to this other issue. Please post your message there.

https://github.com/ollama/ollama/issues/2006

<!-- gh-comment-id:2360131727 --> @igorschlum commented on GitHub (Sep 19, 2024): @liuwq999 It's a matter of the number of simultaneous threads used to pull a model. It was set too high, and although it was lowered, it still wasn't enough. This issue is now closed, and the discussion has moved to this other issue. Please post your message there. https://github.com/ollama/ollama/issues/2006
GiteaMirror commented 2026-04-22 08:41:27 -05:00
Author
Owner
Copy Link

@ifeelsam commented on GitHub (Jan 24, 2025):

i don't exactly know how i solved this but it was dns issue, and it wasn't able to resolve the hostname

so i checked my /etc/systemd/resolved.conf
and i wasn't there

so i just created that file

[Resolve]
DNS=8.8.8.8 8.8.4.4
DNSSEC=no

and restared systemd-resolved

sudo systemctl status systemd-resolved

hope this helps

<!-- gh-comment-id:2611472655 --> @ifeelsam commented on GitHub (Jan 24, 2025): i don't exactly know how i solved this but it was dns issue, and it wasn't able to resolve the hostname so i checked my `/etc/systemd/resolved.conf` and i wasn't there so i just created that file ``` [Resolve] DNS=8.8.8.8 8.8.4.4 DNSSEC=no ``` and restared systemd-resolved ``` sudo systemctl status systemd-resolved ``` hope this helps
GiteaMirror commented 2026-04-22 08:41:27 -05:00
Author
Owner
Copy Link

@Samarth-tate commented on GitHub (Jan 30, 2025):

I had the same issue and fixed it by changing my DNS to (8.8.8.8 & 8.8.4.4). Looks like it was a DNS problem causing the errors. If you're facing this, try switching your DNS in network settings—it worked for me

<!-- gh-comment-id:2623503388 --> @Samarth-tate commented on GitHub (Jan 30, 2025): I had the same issue and fixed it by changing my DNS to (8.8.8.8 & 8.8.4.4). Looks like it was a DNS problem causing the errors. If you're facing this, try switching your DNS in network settings—it worked for me
GiteaMirror commented 2026-04-22 08:41:28 -05:00
Author
Owner
Copy Link

@mdsadiqueinam commented on GitHub (Jan 31, 2025):

Changing the dns does not solve problem for me

<!-- gh-comment-id:2626227682 --> @mdsadiqueinam commented on GitHub (Jan 31, 2025): Changing the dns does not solve problem for me
GiteaMirror commented 2026-04-22 08:41:29 -05:00
Author
Owner
Copy Link

@danyQe commented on GitHub (Jan 31, 2025):

Issue: Unable to Pull Deepseek-R1 Model in Ollama (Windows)

I encountered an issue while trying to pull the deepseek-r1:1.5b model using Ollama on Windows. The download process stalled at 0% and eventually failed with the following error:

ollama pull deepseek-r1:1.5b
pulling manifest
pulling aabd4debf0c8... 0% ▕ ▏ 0 B/1.1 GB
Error: max retries exceeded: Get "aabd4debf0/data": dial tcp: lookup dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com: no such host

Solution

I resolved this issue by changing my DNS server to Cloudflare (1.1.1.1). After making this change, the model pulled successfully.

To change the DNS settings on Windows, refer to this guide:
How to Change Your PC’s DNS Settings on Windows 10.

This solution might help others facing the same issue. Let me know if it works for you!

<!-- gh-comment-id:2626567037 --> @danyQe commented on GitHub (Jan 31, 2025): ## Issue: Unable to Pull Deepseek-R1 Model in Ollama (Windows) I encountered an issue while trying to pull the `deepseek-r1:1.5b` model using Ollama on Windows. The download process stalled at 0% and eventually failed with the following error: ollama pull deepseek-r1:1.5b pulling manifest pulling aabd4debf0c8... 0% ▕ ▏ 0 B/1.1 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/aa/aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250131%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250131T074418Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=710bfefba31d920c37d8d47cd265ef40395d2590d617eafe5f1190f86c261267": dial tcp: lookup dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com: no such host ### Solution I resolved this issue by changing my DNS server to Cloudflare (1.1.1.1). After making this change, the model pulled successfully. To change the DNS settings on Windows, refer to this guide: [How to Change Your PC’s DNS Settings on Windows 10](https://www.windowscentral.com/how-change-your-pcs-dns-settings-windows-10). This solution might help others facing the same issue. Let me know if it works for you!
GiteaMirror commented 2026-04-22 08:41:29 -05:00
Author
Owner
Copy Link

@Amit2001 commented on GitHub (Feb 4, 2025):

Changing DNS helped me to resolve the issue, I was facing a similar issue but after changing DNS, I have successfully installed the model, and it is running perfectly fine.

<!-- gh-comment-id:2634892344 --> @Amit2001 commented on GitHub (Feb 4, 2025): Changing DNS helped me to resolve the issue, I was facing a similar issue but after changing DNS, I have successfully installed the model, and it is running perfectly fine.
GiteaMirror commented 2026-04-22 08:41:30 -05:00
Author
Owner
Copy Link

@sharma-shanu commented on GitHub (Feb 5, 2025):

Changing the dns also solved the issue for me.

<!-- gh-comment-id:2636913879 --> @sharma-shanu commented on GitHub (Feb 5, 2025): Changing the dns also solved the issue for me.
GiteaMirror commented 2026-04-22 08:41:30 -05:00
Author
Owner
Copy Link

@max-keviv commented on GitHub (Feb 6, 2025):

i was also facing this issue in my mac, changing the dns fixed the issue
run this command to fix the issue
sudo networksetup -setdnsservers Wi-Fi 8.8.8.8 8.8.4.4

<!-- gh-comment-id:2639621798 --> @max-keviv commented on GitHub (Feb 6, 2025): i was also facing this issue in my mac, changing the dns fixed the issue run this command to fix the issue sudo networksetup -setdnsservers Wi-Fi 8.8.8.8 8.8.4.4
GiteaMirror commented 2026-04-22 08:41:31 -05:00
Author
Owner
Copy Link

@Marrpee2013 commented on GitHub (Feb 14, 2025):

Image
change DNS didn't work on this issue

<!-- gh-comment-id:2658341806 --> @Marrpee2013 commented on GitHub (Feb 14, 2025): ![Image](https://github.com/user-attachments/assets/32cdeb0c-547f-4d68-a618-ad01dfce2183) change DNS didn't work on this issue
GiteaMirror commented 2026-04-22 08:41:32 -05:00
Author
Owner
Copy Link

@ssingh-teachx commented on GitHub (Feb 16, 2025):

Image change DNS didn't work on this issue

From commands, I am guessing you are using windows machine. I checked this model on my Mac and its working as I had changed dns servers to 8.8.8.8, 8.8.4.4.

It's hard to determine why its not working on yours if you have followed previous suggestions in chat. If you are able to solve it, let us know how u did it. Thanks.

<!-- gh-comment-id:2661347389 --> @ssingh-teachx commented on GitHub (Feb 16, 2025): > ![Image](https://github.com/user-attachments/assets/32cdeb0c-547f-4d68-a618-ad01dfce2183) change DNS didn't work on this issue From commands, I am guessing you are using windows machine. I checked this model on my Mac and its working as I had changed dns servers to 8.8.8.8, 8.8.4.4. It's hard to determine why its not working on yours if you have followed previous suggestions in chat. If you are able to solve it, let us know how u did it. Thanks.
GiteaMirror commented 2026-04-22 08:41:32 -05:00
Author
Owner
Copy Link

@Bhargav-CS commented on GitHub (Feb 16, 2025):

Yeah setting 1.1.1.1 works

<!-- gh-comment-id:2661569418 --> @Bhargav-CS commented on GitHub (Feb 16, 2025): Yeah setting 1.1.1.1 works
GiteaMirror commented 2026-04-22 08:41:33 -05:00
Author
Owner
Copy Link

@Aryan-GNDU commented on GitHub (Mar 1, 2025):

yes if you are facing an error in which the download process stalled at 0% and eventually failed with the following error:

ollama pull (any model)
pulling manifest
pulling aabd4debf0c8... 0% ▕ ▏ 0 B/1.1 GB
Error: max retries exceeded: Get "aabd4debf0/data": dial tcp: lookup dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com: no such host
then if you just change your DNS to Cloudfare then you will be able to pull the model

<!-- gh-comment-id:2692116691 --> @Aryan-GNDU commented on GitHub (Mar 1, 2025): yes if you are facing an error in which the download process stalled at 0% and eventually failed with the following error: ollama pull (any model) pulling manifest pulling aabd4debf0c8... 0% ▕ ▏ 0 B/1.1 GB Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/aa/aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250131%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250131T074418Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=710bfefba31d920c37d8d47cd265ef40395d2590d617eafe5f1190f86c261267": dial tcp: lookup dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com: no such host then if you just change your DNS to Cloudfare then you will be able to pull the model
GiteaMirror commented 2026-04-22 08:41:34 -05:00
Author
Owner
Copy Link

@iamprathamjain commented on GitHub (Mar 2, 2025):

Changing the DNS worked for me on Windows 11
Let me guide you through the steps:

1 Open Control Panel → Network and Internet → Network and Sharing Center.
2 Click Change adapter settings on the left.
3 Right-click your active network connection (Wi-Fi or Ethernet) and select Properties.
4 Choose Internet Protocol Version 4 (TCP/IPv4) and click Properties.
5 Enter the following DNS servers:
Preferred DNS: 8.8.4.4 (Google)
Alternate DNS: 1.1.1.1 (Cloudflare)

6 Save and Retry

<!-- gh-comment-id:2692748395 --> @iamprathamjain commented on GitHub (Mar 2, 2025): Changing the DNS worked for me on Windows 11 Let me guide you through the steps: 1 Open Control Panel → Network and Internet → Network and Sharing Center. 2 Click Change adapter settings on the left. 3 Right-click your active network connection (Wi-Fi or Ethernet) and select Properties. 4 Choose Internet Protocol Version 4 (TCP/IPv4) and click Properties. 5 Enter the following DNS servers: Preferred DNS: 8.8.4.4 (Google) Alternate DNS: 1.1.1.1 (Cloudflare) 6 Save and Retry
GiteaMirror commented 2026-04-22 08:41:34 -05:00
Author
Owner
Copy Link

@rohangore1999 commented on GitHub (Mar 16, 2025):

Changing the DNS for MAC - mac silicon chip

  1. Open System Settings:
  • Click the Apple logo → System Settings (or System Preferences on older macOS versions).
  1. Go to Network Settings:
  • Click Network from the sidebar.
  1. Select Active Network:
  • Choose your active connection (Wi-Fi or Ethernet) → Click Details (or Advanced on older versions).
  1. Go to DNS Tab:
  • In the Details/Advanced window, navigate to the DNS tab.
  1. Add DNS Servers:
  • Click the + button and add:
    • Alternate DNS: 1.1.1.1 (Cloudflare)
  1. Save Changes:
  • Click OK → Apply to save the new DNS settings.
<!-- gh-comment-id:2727355391 --> @rohangore1999 commented on GitHub (Mar 16, 2025): Changing the DNS for MAC - mac silicon chip 1) Open System Settings: - Click the Apple logo → System Settings (or System Preferences on older macOS versions). 2) Go to Network Settings: - Click Network from the sidebar. 3) Select Active Network: - Choose your active connection (Wi-Fi or Ethernet) → Click Details (or Advanced on older versions). 4) Go to DNS Tab: - In the Details/Advanced window, navigate to the DNS tab. 5) Add DNS Servers: - Click the + button and add: - Alternate DNS: 1.1.1.1 (Cloudflare) 6) Save Changes: - Click OK → Apply to save the new DNS settings.
GiteaMirror commented 2026-04-22 08:41:35 -05:00
Author
Owner
Copy Link

@cptiwari20 commented on GitHub (Mar 18, 2025):

https://github.com/ollama/ollama/issues/6211#issuecomment-2727355391
This worked for me,
thanks @rohangore1999

<!-- gh-comment-id:2731568117 --> @cptiwari20 commented on GitHub (Mar 18, 2025): https://github.com/ollama/ollama/issues/6211#issuecomment-2727355391 This worked for me, thanks @rohangore1999
GiteaMirror commented 2026-04-22 08:41:35 -05:00
Author
Owner
Copy Link

@endual commented on GitHub (Apr 21, 2025):

I have the same exception，and solved as follow:

ollama run hf.co/{username}/{reponame}:latest
replaced by
ollama run hf-mirror.com/{username}/{reponame}:latest

<!-- gh-comment-id:2817655835 --> @endual commented on GitHub (Apr 21, 2025): I have the same exception，and solved as follow: ollama run **hf.co**/{username}/{reponame}:latest replaced by ollama run **hf-mirror.com**/{username}/{reponame}:latest
GiteaMirror commented 2026-04-22 08:41:37 -05:00
Author
Owner
Copy Link

@eust-w commented on GitHub (May 14, 2025):

I have the same exception，and solved as follow:

ollama run hf.co/{username}/{reponame}:latest replaced by ollama run hf-mirror.com/{username}/{reponame}:latest

This solution is effective

<!-- gh-comment-id:2878507263 --> @eust-w commented on GitHub (May 14, 2025): > I have the same exception，and solved as follow: > > ollama run **hf.co**/{username}/{reponame}:latest replaced by ollama run **hf-mirror.com**/{username}/{reponame}:latest This solution is effective
GiteaMirror commented 2026-04-22 08:41:37 -05:00
Author
Owner
Copy Link

@SrLeet03 commented on GitHub (May 14, 2025):

I had the same issue , turned out to be a DNS problem.

Switching to Google’s public DNS (8.8.8.8 & 8.8.4.4) fixed it for me.

On macOS:
System Settings > Network > Wi-Fi > Details > DNS > Add 8.8.8.8 & 8.8.4.4.

Then simply turn off your WIFI/LAN and reconnect with it and to confirm use scutil --dns if DNS got added.

<!-- gh-comment-id:2881538972 --> @SrLeet03 commented on GitHub (May 14, 2025): I had the same issue , turned out to be a DNS problem. Switching to Google’s public DNS (8.8.8.8 & 8.8.4.4) fixed it for me. **On macOS:** System Settings > Network > Wi-Fi > Details > DNS > Add 8.8.8.8 & 8.8.4.4. Then simply turn off your WIFI/LAN and reconnect with it and to confirm use **scutil --dns** if DNS got added.
GiteaMirror commented 2026-04-22 08:41:39 -05:00
Author
Owner
Copy Link

@Penguin5681 commented on GitHub (Jul 6, 2025):

I had the same issue and fixed it by changing my DNS to (8.8.8.8 & 8.8.4.4). Looks like it was a DNS problem causing the errors. If you're facing this, try switching your DNS in network settings—it worked for me

It did turn to be a dns issue, lol.
Thanks for figuring it out

<!-- gh-comment-id:3042042327 --> @Penguin5681 commented on GitHub (Jul 6, 2025): > I had the same issue and fixed it by changing my DNS to (8.8.8.8 & 8.8.4.4). Looks like it was a DNS problem causing the errors. If you're facing this, try switching your DNS in network settings—it worked for me It did turn to be a dns issue, lol. Thanks for figuring it out
GiteaMirror commented 2026-04-22 08:41:39 -05:00
Author
Owner
Copy Link

@zadescoxp commented on GitHub (Aug 23, 2025):

Just change the DNS, use this command
sudo networksetup -setdnsservers Wi-Fi 8.8.8.8 8.8.4.4

<!-- gh-comment-id:3216234977 --> @zadescoxp commented on GitHub (Aug 23, 2025): Just change the DNS, use this command `sudo networksetup -setdnsservers Wi-Fi 8.8.8.8 8.8.4.4`
GiteaMirror commented 2026-04-22 08:41:41 -05:00
Author
Owner
Copy Link

@PriDebnath commented on GitHub (Aug 23, 2025):

Changing the DNS for MAC - mac silicon chip

  1. Open System Settings:
  • Click the Apple logo → System Settings (or System Preferences on older macOS versions).
  1. Go to Network Settings:
  • Click Network from the sidebar.
  1. Select Active Network:
  • Choose your active connection (Wi-Fi or Ethernet) → Click Details (or Advanced on older versions).
  1. Go to DNS Tab:
  • In the Details/Advanced window, navigate to the DNS tab.
  1. Add DNS Servers:

  • Click the + button and add:

    • Alternate DNS: 1.1.1.1 (Cloudflare)
  1. Save Changes:
  • Click OK → Apply to save the new DNS settings.

Thank you @rohangore1999

<!-- gh-comment-id:3216566532 --> @PriDebnath commented on GitHub (Aug 23, 2025): > Changing the DNS for MAC - mac silicon chip > > 1. Open System Settings: > > * Click the Apple logo → System Settings (or System Preferences on older macOS versions). > > 2. Go to Network Settings: > > * Click Network from the sidebar. > > 3. Select Active Network: > > * Choose your active connection (Wi-Fi or Ethernet) → Click Details (or Advanced on older versions). > > 4. Go to DNS Tab: > > * In the Details/Advanced window, navigate to the DNS tab. > > 5. Add DNS Servers: > > * Click the + button and add: > > * Alternate DNS: 1.1.1.1 (Cloudflare) > > 6. Save Changes: > > * Click OK → Apply to save the new DNS settings. Thank you @rohangore1999
GiteaMirror commented 2026-04-22 08:41:43 -05:00
Author
Owner
Copy Link

@anton-karlovskiy commented on GitHub (Sep 16, 2025):

@mdsadiqueinam @ziyouzhea @rampageservices @dkgaraujo @igorschlum

👋 I’ve been trying to download llama3.2 on Windows 11 (ollama run llama3.2) and keep running into issues:

  • An existing connection was forcibly closed by the remote host
  • Error: max retries exceeded

What I’ve tried so far:

Image

From what I can tell, the main culprit seems to be an unstable connection. The workaround right now is to just re-run the command until it eventually completes, but this gets tedious.

To automate retries, I wrapped it in a small script. Sharing here in case it helps others or the devs want to consider integrating retry logic directly:

Windows
Open new notepad and put this code.

@echo off
:loop
echo Running ollama run llama3.2...
ollama run llama3.2

if %errorlevel% neq 0 (
    echo The command failed. Retrying... Press Ctrl+C to exit.
    goto loop
)
echo The command completed successfully!

Next go to save as… and pick All files as file type and name the file with .bat extension.
And finally you can run it.
To edit the code above, just change model name from llama3.2 to any other model you like.

Linux
I didn’t test the code for Linux but this should hopefully work.

#!/bin/bash

# Function to handle Ctrl+C
trap 'echo "Script terminated by user. Exiting..."; exit' SIGINT
while true; do
    echo "Running ollama run llama3.2..."
    ollama run llama3.2
    if [ $? -eq 0 ]; then
        echo "The command completed successfully!"
        break
    else
        echo "The command failed. Retrying... Press Ctrl+C to exit."
    fi
done

Save this as run_loop.sh then run these commands.

chmod +x run_loop.sh

./run_loop.sh

Re: https://medium.com/@timnirmal/ollama-max-retries-exceeded-error-de6e0f86383e

Good luck 🤞

<!-- gh-comment-id:3295829208 --> @anton-karlovskiy commented on GitHub (Sep 16, 2025): @mdsadiqueinam @ziyouzhea @rampageservices @dkgaraujo @igorschlum 👋 I’ve been trying to download llama3.2 on Windows 11 (ollama run llama3.2) and keep running into issues: - An existing connection was forcibly closed by the remote host - Error: max retries exceeded What I’ve tried so far: - https://github.com/ollama/ollama/issues/3769#issuecomment-2076767384: closed VPN → no change - https://github.com/ollama/ollama/issues/6211#issuecomment-2626567037: changed DNS → made some progress (got to ~37%) but stuck again <img width="1086" height="124" alt="Image" src="https://github.com/user-attachments/assets/774acce1-b0af-4b66-b2ae-415baf6f0fe0" /> From what I can tell, the main culprit seems to be an unstable connection. The workaround right now is to just re-run the command until it eventually completes, but this gets tedious. To automate retries, I wrapped it in a small script. Sharing here in case it helps others or the devs want to consider integrating retry logic directly: **Windows** Open new notepad and put this code. ```bash @echo off :loop echo Running ollama run llama3.2... ollama run llama3.2 if %errorlevel% neq 0 ( echo The command failed. Retrying... Press Ctrl+C to exit. goto loop ) echo The command completed successfully! ``` Next go to save as… and pick All files as file type and name the file with `.bat` extension. And finally you can run it. To edit the code above, just change model name from `llama3.2` to any other model you like. **Linux** I didn’t test the code for Linux but this should hopefully work. #!/bin/bash ```bash # Function to handle Ctrl+C trap 'echo "Script terminated by user. Exiting..."; exit' SIGINT while true; do echo "Running ollama run llama3.2..." ollama run llama3.2 if [ $? -eq 0 ]; then echo "The command completed successfully!" break else echo "The command failed. Retrying... Press Ctrl+C to exit." fi done ``` Save this as `run_loop.sh` then run these commands. ```bash chmod +x run_loop.sh ``` ```bash ./run_loop.sh ``` Re: https://medium.com/@timnirmal/ollama-max-retries-exceeded-error-de6e0f86383e Good luck 🤞
GiteaMirror commented 2026-04-22 08:41:43 -05:00
Author
Owner
Copy Link

@Shivamp9 commented on GitHub (Oct 5, 2025):

restarted wifi router and worked for me.

<!-- gh-comment-id:3368805601 --> @Shivamp9 commented on GitHub (Oct 5, 2025): restarted wifi router and worked for me.
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#29640
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?