github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13770] Cloud model connection timeout when using official Ollama client #55538

New Issue
Open
opened 2026-04-29 09:22:14 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-29 09:22:14 -05:00
Owner
Copy Link

Originally created by @chenchongming512 on GitHub (Jan 19, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13770

What is the issue?

Description

When trying to use cloud models in the official Ollama client, I'm getting a connection timeout error.

Steps to Reproduce

  1. Open Ollama official client
  2. Attempt to use any cloud model
  3. Get connection timeout error

Error Message

500 Internal Server Error: Post "https://ollama.com:443/api/chat?ts=1768793788": dial tcp 34.36.133.15:443: i/o timeout

What I've Tried

  1. Restarted Ollama client
  2. Checked internet connection
  3. Local model are fine

Additional Information

PING ollama.com (34.36.133.15): 56 data bytes
64 bytes from 34.36.133.15: icmp_seq=0 ttl=104 time=223.880 ms
64 bytes from 34.36.133.15: icmp_seq=1 ttl=104 time=231.907 ms
64 bytes from 34.36.133.15: icmp_seq=2 ttl=104 time=251.540 ms
64 bytes from 34.36.133.15: icmp_seq=3 ttl=104 time=298.792 ms
64 bytes from 34.36.133.15: icmp_seq=4 ttl=104 time=228.120 ms
--- ollama.com ping statistics ---
5 packets transmitted, 5 packets received, 0.0% packet loss

Questions

Are cloud models currently available ?

Relevant log output

[GIN] 2026/01/19 - 11:38:28 | 200 |    5.825583ms |       127.0.0.1 | GET      "/api/tags"
time=2026-01-19T11:38:44.419+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793894\": dial tcp 34.36.133.15:443: i/o timeout"
[GIN] 2026/01/19 - 11:38:44 | 200 |  30.00169625s |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/01/19 - 11:38:58 | 200 |     6.76375ms |       127.0.0.1 | GET      "/api/tags"
time=2026-01-19T11:39:14.928+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793924\": dial tcp 34.36.133.15:443: i/o timeout"
[GIN] 2026/01/19 - 11:39:14 | 200 | 30.001228208s |       127.0.0.1 | POST     "/api/me"
time=2026-01-19T11:39:16.281+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793955\": read tcp 10.10.55.16:57012->34.36.133.15:443: read: connection reset by peer"
[GIN] 2026/01/19 - 11:39:16 | 200 |  346.957916ms |       127.0.0.1 | POST     "/api/me"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

Version 0.14.2

Originally created by @chenchongming512 on GitHub (Jan 19, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13770 ### What is the issue? ## Description When trying to use cloud models in the official Ollama client, I'm getting a connection timeout error. ## Steps to Reproduce 1. Open Ollama official client 2. Attempt to use any cloud model 3. Get connection timeout error ## Error Message 500 Internal Server Error: Post "[https://ollama.com:443/api/chat?ts=1768793788](https://ollama.com/api/chat?ts=1768793788)": dial tcp 34.36.133.15:443: i/o timeout ## What I've Tried 1. Restarted Ollama client 2. Checked internet connection 3. Local model are fine ## Additional Information PING ollama.com (34.36.133.15): 56 data bytes 64 bytes from 34.36.133.15: icmp_seq=0 ttl=104 time=223.880 ms 64 bytes from 34.36.133.15: icmp_seq=1 ttl=104 time=231.907 ms 64 bytes from 34.36.133.15: icmp_seq=2 ttl=104 time=251.540 ms 64 bytes from 34.36.133.15: icmp_seq=3 ttl=104 time=298.792 ms 64 bytes from 34.36.133.15: icmp_seq=4 ttl=104 time=228.120 ms --- ollama.com ping statistics --- 5 packets transmitted, 5 packets received, 0.0% packet loss ## Questions Are cloud models currently available ? ### Relevant log output ```shell [GIN] 2026/01/19 - 11:38:28 | 200 | 5.825583ms | 127.0.0.1 | GET "/api/tags" time=2026-01-19T11:38:44.419+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793894\": dial tcp 34.36.133.15:443: i/o timeout" [GIN] 2026/01/19 - 11:38:44 | 200 | 30.00169625s | 127.0.0.1 | POST "/api/me" [GIN] 2026/01/19 - 11:38:58 | 200 | 6.76375ms | 127.0.0.1 | GET "/api/tags" time=2026-01-19T11:39:14.928+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793924\": dial tcp 34.36.133.15:443: i/o timeout" [GIN] 2026/01/19 - 11:39:14 | 200 | 30.001228208s | 127.0.0.1 | POST "/api/me" time=2026-01-19T11:39:16.281+08:00 level=ERROR source=routes.go:1809 msg="Post \"https://ollama.com/api/me?ts=1768793955\": read tcp 10.10.55.16:57012->34.36.133.15:443: read: connection reset by peer" [GIN] 2026/01/19 - 11:39:16 | 200 | 346.957916ms | 127.0.0.1 | POST "/api/me" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version Version 0.14.2
GiteaMirror added the bug label 2026-04-29 09:22:14 -05:00
GiteaMirror commented 2026-04-29 09:22:16 -05:00
Author
Owner
Copy Link

@venidicii commented on GitHub (Jan 19, 2026):

Maybe only the IP in the Chinese Mainland is affected.

<!-- gh-comment-id:3766876580 --> @venidicii commented on GitHub (Jan 19, 2026): Maybe only the IP in the Chinese Mainland is affected.
GiteaMirror commented 2026-04-29 09:22:17 -05:00
Author
Owner
Copy Link

@chenchongming512 commented on GitHub (Jan 19, 2026):

But it couldn't work even with VPN

<!-- gh-comment-id:3767495857 --> @chenchongming512 commented on GitHub (Jan 19, 2026): But it couldn't work even with VPN
GiteaMirror commented 2026-04-29 09:22:17 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 19, 2026):

Cloud models appear to be working fine.

$ OLLAMA_HOST=ollama.com ollama run rnj-1:8b hello
Hello! How can I assist you today?
$ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello
Hello! How can I help you today?
$ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1:671b hello --think=false
Hello! 😊 How can I help you today?
$ OLLAMA_HOST=ollama.com ollama run mistral-large-3:675b hello 
Hello! 😊 How can I assist you today? Whether you have a question, need help with something, or just want to chat, I'm here for you!
<!-- gh-comment-id:3768765627 --> @rick-github commented on GitHub (Jan 19, 2026): Cloud models appear to be working fine. ```console $ OLLAMA_HOST=ollama.com ollama run rnj-1:8b hello Hello! How can I assist you today? $ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello Hello! How can I help you today? $ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1:671b hello --think=false Hello! 😊 How can I help you today? $ OLLAMA_HOST=ollama.com ollama run mistral-large-3:675b hello Hello! 😊 How can I assist you today? Whether you have a question, need help with something, or just want to chat, I'm here for you! ```
GiteaMirror commented 2026-04-29 09:22:18 -05:00
Author
Owner
Copy Link

@venidicii commented on GitHub (Jan 19, 2026):

Cloud models appear to be working fine.

$ OLLAMA_HOST=ollama.com ollama run rnj-1:8b hello
Hello! How can I assist you today?
$ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello
Hello! How can I help you today?
$ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1:671b hello --think=false
Hello! 😊 How can I help you today?
$ OLLAMA_HOST=ollama.com ollama run mistral-large-3:675b hello
Hello! 😊 How can I assist you today? Whether you have a question, need help with something, or just want to chat, I'm here for you!

$ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello
Error: Head "https://ollama.com:443/?ts=1768841986": read tcp 192.168.2.88:44968->34.36.133.15:443: read: connection reset by peer

My ip: 61.159.205.76.

<!-- gh-comment-id:3769381472 --> @venidicii commented on GitHub (Jan 19, 2026): > Cloud models appear to be working fine. > > $ OLLAMA_HOST=ollama.com ollama run rnj-1:8b hello > Hello! How can I assist you today? > $ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello > Hello! How can I help you today? > $ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1:671b hello --think=false > Hello! 😊 How can I help you today? > $ OLLAMA_HOST=ollama.com ollama run mistral-large-3:675b hello > Hello! 😊 How can I assist you today? Whether you have a question, need help with something, or just want to chat, I'm here for you! $ OLLAMA_HOST=ollama.com ollama run kimi-k2:1t hello Error: Head "https://ollama.com:443/?ts=1768841986": read tcp 192.168.2.88:44968->34.36.133.15:443: read: connection reset by peer My ip: 61.159.205.76.
GiteaMirror commented 2026-04-29 09:22:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 19, 2026):

I think you'll have to take it up with your Internet Service Provider or the administration of the Great Firewall.

<!-- gh-comment-id:3769432612 --> @rick-github commented on GitHub (Jan 19, 2026): I think you'll have to take it up with your Internet Service Provider or the administration of the Great Firewall.
GiteaMirror commented 2026-04-29 09:22:19 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Jan 19, 2026):

@chenchongming512
Looks like a timeout / network edge issue, try running npx ai-patch doctor to see what the solution is?

<!-- gh-comment-id:3770292912 --> @ghost commented on GitHub (Jan 19, 2026): @chenchongming512 Looks like a timeout / network edge issue, try running `npx ai-patch doctor` to see what the solution is?
GiteaMirror commented 2026-04-29 09:22:20 -05:00
Author
Owner
Copy Link

@fuhua2019 commented on GitHub (Jan 20, 2026):

When using the Ollama client to access cloud models, it returns the following error:
500 Internal Server Error: Post "https://ollama.com:443/api/chat?ts=1768919723
": read tcp 192.168.3.77:52104->34.36.133.15:443: read: connection reset by peer.
However, the Ollama official website (https://ollama.com/
) is accessible normally via a browser.
Has anyone started tracking or resolving this issue?

<!-- gh-comment-id:3773226070 --> @fuhua2019 commented on GitHub (Jan 20, 2026): When using the Ollama client to access cloud models, it returns the following error: 500 Internal Server Error: Post "[https://ollama.com:443/api/chat?ts=1768919723](https://ollama.com/api/chat?ts=1768919723) ": read tcp 192.168.3.77:52104->34.36.133.15:443: read: connection reset by peer. However, the Ollama official website (https://ollama.com/ ) is accessible normally via a browser. Has anyone started tracking or resolving this issue?
GiteaMirror commented 2026-04-29 09:22:20 -05:00
Author
Owner
Copy Link

@speedyfoxai commented on GitHub (Feb 28, 2026):

Adding another data point — seeing the same issue today (Feb 28, 2026). Cloud models (specifically kimi-k2.5:cloud) load successfully but produce no response. Other cloud models like minimax work fine, so it appears model-specific or related to particular cloud hardware allocation. No errors in logs, just silent failures.

<!-- gh-comment-id:3977911842 --> @speedyfoxai commented on GitHub (Feb 28, 2026): Adding another data point — seeing the same issue today (Feb 28, 2026). Cloud models (specifically kimi-k2.5:cloud) load successfully but produce no response. Other cloud models like minimax work fine, so it appears model-specific or related to particular cloud hardware allocation. No errors in logs, just silent failures.
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#55538
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?