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 #6173] Using ollama version 0.3.3, downloading all models will result in errors. #3856

New Issue
Open
opened 2026-04-12 14:41:38 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-12 14:41:38 -05:00
Owner
Copy Link

Originally created by @ucjmhfeng on GitHub (Aug 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6173

What is the issue?

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/gemma2/manifests/2b": net/http: TLS handshake timeout.
Before version 0.3.0, there were no similar issues. Starting from the update to 0.3.1, I tried many methods, but none of them worked, including using VPN and reinstalling Olama.

OS

Linux

GPU

Other

CPU

Intel

Ollama version

0.3.3

Originally created by @ucjmhfeng on GitHub (Aug 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6173 ### What is the issue? pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/gemma2/manifests/2b": net/http: TLS handshake timeout. Before version 0.3.0, there were no similar issues. Starting from the update to 0.3.1, I tried many methods, but none of them worked, including using VPN and reinstalling Olama. ### OS Linux ### GPU Other ### CPU Intel ### Ollama version 0.3.3
GiteaMirror added the bug label 2026-04-12 14:41:38 -05:00
GiteaMirror commented 2026-04-12 14:41:39 -05:00
Author
Owner
Copy Link

@ucjmhfeng commented on GitHub (Aug 5, 2024):

My network is accessible https://registry.ollama.ai/ Website.

<!-- gh-comment-id:2268470545 --> @ucjmhfeng commented on GitHub (Aug 5, 2024): My network is accessible https://registry.ollama.ai/ Website.
GiteaMirror commented 2026-04-12 14:41:40 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 5, 2024):

@ucjmhfeng Does the model begin to load, or does the error occur before it starts?

<!-- gh-comment-id:2269360423 --> @igorschlum commented on GitHub (Aug 5, 2024): @ucjmhfeng Does the model begin to load, or does the error occur before it starts?
GiteaMirror commented 2026-04-12 14:41:40 -05:00
Author
Owner
Copy Link

@ucjmhfeng commented on GitHub (Aug 6, 2024):

@igorschlum
An error occurred after running "ollama run gemma2:2b".
pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/gemma2/manifests/2b": net/http: TLS handshake timeout.

<!-- gh-comment-id:2270260673 --> @ucjmhfeng commented on GitHub (Aug 6, 2024): @igorschlum An error occurred after running "ollama run gemma2:2b". pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/gemma2/manifests/2b": net/http: TLS handshake timeout.
GiteaMirror commented 2026-04-12 14:41:41 -05:00
Author
Owner
Copy Link

@alwqx commented on GitHub (Aug 6, 2024):

I test it on my Linux macine with ollama version 0.3.3. It works well for me.

# alwqx @ node in ~ [2:42:20]
$ ollama --version
ollama version is 0.3.3

# alwqx @ node in ~ [2:42:22]
$ ollama pull gemma2:2b
pulling manifest
pulling 7462734796d6... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.6 GB
pulling e0a42594d802... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏  358 B
pulling 097a36493f71... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB
pulling 2490e7468436... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏   65 B
pulling e18ad7af7efb... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏  487 B
verifying sha256 digest
writing manifest
removing any unused layers
success

# alwqx @ node in ~ [2:43:38]
$ ollama list
NAME     	ID          	SIZE  	MODIFIED
gemma2:2b	8ccf136fdd52	1.6 GB	12 seconds ago

I search on Google with net/http: TLS handshake timeout, This problem may related to proxy config, I suggest check your proxy setting refering bellow links:

<!-- gh-comment-id:2270515377 --> @alwqx commented on GitHub (Aug 6, 2024): I test it on my Linux macine with ollama `version 0.3.3`. It works well for me. ```shell # alwqx @ node in ~ [2:42:20] $ ollama --version ollama version is 0.3.3 # alwqx @ node in ~ [2:42:22] $ ollama pull gemma2:2b pulling manifest pulling 7462734796d6... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.6 GB pulling e0a42594d802... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 358 B pulling 097a36493f71... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB pulling 2490e7468436... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 65 B pulling e18ad7af7efb... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████▏ 487 B verifying sha256 digest writing manifest removing any unused layers success # alwqx @ node in ~ [2:43:38] $ ollama list NAME ID SIZE MODIFIED gemma2:2b 8ccf136fdd52 1.6 GB 12 seconds ago ``` I search on Google with `net/http: TLS handshake timeout`, This problem may related to **proxy config**, I suggest check your proxy setting refering bellow links: - [Unable to connect to the server: net/http: TLS handshake timeout](https://stackoverflow.com/questions/59958274/unable-to-connect-to-the-server-net-http-tls-handshake-timeout) - [How to resolve a TLS handshake timeout error when adding an app repository on a downstream cluster](https://www.suse.com/support/kb/doc/?id=000021019)
GiteaMirror commented 2026-04-12 14:41:41 -05:00
Author
Owner
Copy Link

@skh1949 commented on GitHub (Aug 6, 2024):

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2/manifests/1.5b": read tcp 192.168.0.107:65240->172.67.182.229:443: wsarecv: An existing connection was forcibly closed by the remote host.求解

<!-- gh-comment-id:2270910341 --> @skh1949 commented on GitHub (Aug 6, 2024): pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2/manifests/1.5b": read tcp 192.168.0.107:65240->172.67.182.229:443: wsarecv: An existing connection was forcibly closed by the remote host.求解
GiteaMirror commented 2026-04-12 14:41:42 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 6, 2024):

It appears that the error you're experiencing is related to network connectivity issues, rather than a bug in the software. Specifically, the error message:

Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2/manifests/1.5b": read tcp 192.168.0.107:65240->172.67.182.229:443: wsarecv: An existing connection was forcibly closed by the remote host.
suggests that the connection to the remote host is being forcibly closed. This type of error is often due to network restrictions or limitations that may be in place in your environment. Common causes include:

University or Corporate Networks: Many educational institutions and companies implement strict network policies that can block or restrict access to certain external resources. This might be the cause if you're trying to access the registry from within such a network.
Country-Level Restrictions: Some countries have internet regulations that limit access to certain websites and services. If you are located in a region with such restrictions, this could be preventing a successful connection.
To troubleshoot this issue, you might try the following steps:

Check Network Policies: If you are using a network managed by your university or company, contact your network administrator to see if there are any restrictions on accessing external resources. They may be able to whitelist the necessary domains.
Use a VPN: A VPN can sometimes bypass network restrictions. If you suspect country-level restrictions, a VPN might help in establishing the required connection.
Test from a Different Network: Try accessing the resource from a different network, such as a home network or a mobile hotspot, to see if the issue persists. This can help identify if the problem is specific to your current network.
Check Firewall Settings: Ensure that your firewall is not blocking the connection. Sometimes, personal or local firewalls can inadvertently block legitimate traffic.
We hope this helps clarify the situation. If the problem persists after trying these steps, please let us know, and we can explore further options.

<!-- gh-comment-id:2270928044 --> @igorschlum commented on GitHub (Aug 6, 2024): It appears that the error you're experiencing is related to network connectivity issues, rather than a bug in the software. Specifically, the error message: Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/qwen2/manifests/1.5b": read tcp 192.168.0.107:65240->172.67.182.229:443: wsarecv: An existing connection was forcibly closed by the remote host. suggests that the connection to the remote host is being forcibly closed. This type of error is often due to network restrictions or limitations that may be in place in your environment. Common causes include: University or Corporate Networks: Many educational institutions and companies implement strict network policies that can block or restrict access to certain external resources. This might be the cause if you're trying to access the registry from within such a network. Country-Level Restrictions: Some countries have internet regulations that limit access to certain websites and services. If you are located in a region with such restrictions, this could be preventing a successful connection. To troubleshoot this issue, you might try the following steps: Check Network Policies: If you are using a network managed by your university or company, contact your network administrator to see if there are any restrictions on accessing external resources. They may be able to whitelist the necessary domains. Use a VPN: A VPN can sometimes bypass network restrictions. If you suspect country-level restrictions, a VPN might help in establishing the required connection. Test from a Different Network: Try accessing the resource from a different network, such as a home network or a mobile hotspot, to see if the issue persists. This can help identify if the problem is specific to your current network. Check Firewall Settings: Ensure that your firewall is not blocking the connection. Sometimes, personal or local firewalls can inadvertently block legitimate traffic. We hope this helps clarify the situation. If the problem persists after trying these steps, please let us know, and we can explore further options.
GiteaMirror commented 2026-04-12 14:41:43 -05:00
Author
Owner
Copy Link

@gaby commented on GitHub (Aug 30, 2024):

@ucjmhfeng Are you using a Proxy? I have the same error. Any other tool works fine by just setting HTTP_PROXY, HTTPS_PROXY. Ollama on the other hand gets all these weird errors.

<!-- gh-comment-id:2321096671 --> @gaby commented on GitHub (Aug 30, 2024): @ucjmhfeng Are you using a Proxy? I have the same error. Any other tool works fine by just setting HTTP_PROXY, HTTPS_PROXY. Ollama on the other hand gets all these weird errors.
GiteaMirror commented 2026-04-12 14:41:43 -05:00
Author
Owner
Copy Link

@Kydon-ai commented on GitHub (Oct 10, 2025):

me too：
PS C:\Users\xxx> ollama run qwen
pulling manifest
Error: max retries exceeded: Get "46bb65206e/data": net/http: TLS handshake timeout

<!-- gh-comment-id:3389621901 --> @Kydon-ai commented on GitHub (Oct 10, 2025): me too： PS C:\Users\xxx> ollama run qwen pulling manifest Error: max retries exceeded: Get "https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/46/46bb65206e0e2b00424f33985a5281bd21070617ebcfda9be86eb17e6e00f793/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20251010%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20251010T113548Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=5bdde726b5071cbf865b6c69b00c5e84e81bbcaf7847c0a5664153217b3b7f44": net/http: TLS handshake timeout
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#3856
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?