github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12799] ollama cloud models aren't working #34249

New Issue
Open
opened 2026-04-22 17:41:16 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-04-22 17:41:16 -05:00
Owner
Copy Link

Originally created by @PCUser2022 on GitHub (Oct 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12799

Originally assigned to: @gr4ceG on GitHub.

What is the issue?

Cloud models are broken for me.

Connecting to 'qwen3-vl:235b' on 'ollama.com' ⚡
>>> What's the best artifact set for Hu Tao?
Error: 500 Internal Server Error: unmarshal: invalid character 'I' looking for beginning of value

Ollama is failing to decode the server response.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.3

Originally created by @PCUser2022 on GitHub (Oct 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12799 Originally assigned to: @gr4ceG on GitHub. ### What is the issue? Cloud models are broken for me. ``` Connecting to 'qwen3-vl:235b' on 'ollama.com' ⚡ >>> What's the best artifact set for Hu Tao? Error: 500 Internal Server Error: unmarshal: invalid character 'I' looking for beginning of value ``` Ollama is failing to decode the server response. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.3
GiteaMirror added the bug label 2026-04-22 17:41:16 -05:00
GiteaMirror commented 2026-04-22 17:41:17 -05:00
Author
Owner
Copy Link

@theuncivilizedarchive commented on GitHub (Oct 28, 2025):

Are you able to update the Ollama version? That might be one of the issues.
But, the error 500 is an internal server error, so it can either be because of some sort of issue or maintenance on Ollama's part, or, maybe a timeout or resource exhaustion.

Also the model your are using, the qwen3-vl:235b is a very large model, and other people have had issues with it. Try using other models such as llama3:8b

<!-- gh-comment-id:3457414875 --> @theuncivilizedarchive commented on GitHub (Oct 28, 2025): Are you able to update the Ollama version? That might be one of the issues. But, the error 500 is an internal server error, so it can either be because of some sort of issue or maintenance on Ollama's part, or, maybe a timeout or resource exhaustion. Also the model your are using, the qwen3-vl:235b is a very large model, and other people have had issues with it. Try using other models such as llama3:8b
GiteaMirror commented 2026-04-22 17:41:17 -05:00
Author
Owner
Copy Link

@marabgol commented on GitHub (Oct 29, 2025):

I have the same issue on MacOS M2/3 no mater how small or big the model is the same 500 error, even I downloaded GGUF from successful reported qwen3-VL , they have the issue with current ollama version.

<!-- gh-comment-id:3460411760 --> @marabgol commented on GitHub (Oct 29, 2025): I have the same issue on MacOS M2/3 no mater how small or big the model is the same 500 error, even I downloaded GGUF from successful reported qwen3-VL , they have the issue with current ollama version.
GiteaMirror commented 2026-04-22 17:41:18 -05:00
Author
Owner
Copy Link

@pankaj89 commented on GitHub (Oct 29, 2025):

Same for me i am checking on M4 Mac mini when trying to run minimax m2 cloud

ollama run minimax-m2:cloud

failed with

Error: 500 Internal Server Error: unmarshal: invalid character 'I' looking for beginning of value

Edited:
Fixed by loging on ollama as its cloud model

<!-- gh-comment-id:3463598314 --> @pankaj89 commented on GitHub (Oct 29, 2025): Same for me i am checking on M4 Mac mini when trying to run minimax m2 cloud ``` ollama run minimax-m2:cloud ``` failed with ``` Error: 500 Internal Server Error: unmarshal: invalid character 'I' looking for beginning of value ``` Edited: Fixed by loging on ollama as its cloud model
GiteaMirror commented 2026-04-22 17:41:18 -05:00
Author
Owner
Copy Link

@jaeyoung0509 commented on GitHub (Oct 30, 2025):

I'm experiencing the same issue with the Qwen series models

<!-- gh-comment-id:3466379621 --> @jaeyoung0509 commented on GitHub (Oct 30, 2025): I'm experiencing the same issue with the Qwen series models
GiteaMirror commented 2026-04-22 17:41:19 -05:00
Author
Owner
Copy Link

@theDiverDK commented on GitHub (Oct 30, 2025):

Same issue with minmax-m2:cloud :(

<!-- gh-comment-id:3466519470 --> @theDiverDK commented on GitHub (Oct 30, 2025): Same issue with minmax-m2:cloud :(
GiteaMirror commented 2026-04-22 17:41:19 -05:00
Author
Owner
Copy Link

@matthewoates commented on GitHub (Oct 30, 2025):

I had this issue when attempting to run minimax-m2:cloud for free during the short term promotion. I had never logged in before.

The fix for me as mentioned by @pankaj89 was to log in. A more accurate error message would be helpful here.

<!-- gh-comment-id:3470267678 --> @matthewoates commented on GitHub (Oct 30, 2025): I had this issue when attempting to run `minimax-m2:cloud` for free during the short term promotion. I had never logged in before. The fix for me as mentioned by @pankaj89 was to log in. A more accurate error message would be helpful here.
GiteaMirror commented 2026-04-22 17:41:20 -05:00
Author
Owner
Copy Link

@theDiverDK commented on GitHub (Oct 31, 2025):

This morning it worked, but 'brew upgrade' did install a new ollama version, maybe the bug is fixed?

<!-- gh-comment-id:3471523717 --> @theDiverDK commented on GitHub (Oct 31, 2025): This morning it worked, but 'brew upgrade' did install a new ollama version, maybe the bug is fixed?
GiteaMirror commented 2026-04-22 17:41:20 -05:00
Author
Owner
Copy Link

@PCUser2022 commented on GitHub (Oct 31, 2025):

The issue happens randomly. It sometimes starts working, but after some time it breaks again.

<!-- gh-comment-id:3473657452 --> @PCUser2022 commented on GitHub (Oct 31, 2025): The issue happens randomly. It sometimes starts working, but after some time it breaks again.
GiteaMirror commented 2026-04-22 17:41:21 -05:00
Author
Owner
Copy Link

@bosborne commented on GitHub (Nov 1, 2025):

Same issue, with minimax-m2. Latest ollama, 0.12.9 on MacOS Tahoe 26.0.1

<!-- gh-comment-id:3476677928 --> @bosborne commented on GitHub (Nov 1, 2025): Same issue, with minimax-m2. Latest ollama, 0.12.9 on MacOS Tahoe 26.0.1
GiteaMirror commented 2026-04-22 17:41:21 -05:00
Author
Owner
Copy Link

@abulka commented on GitHub (Nov 8, 2025):

  • In terminal: ollama run kimi-k2:1t-cloud → Works correctly
  • In Ollama GUI: Select kimi-k2:1t-cloud from model list → Error occurs

Expected Behavior: Model should run in GUI as it does via terminal

<!-- gh-comment-id:3506494588 --> @abulka commented on GitHub (Nov 8, 2025): - In terminal: `ollama run kimi-k2:1t-cloud` → Works correctly - In Ollama GUI: Select `kimi-k2:1t-cloud` from model list → Error occurs Expected Behavior: Model should run in GUI as it does via terminal
GiteaMirror commented 2026-04-22 17:41:22 -05:00
Author
Owner
Copy Link

@electroheadfx commented on GitHub (Feb 26, 2026):

ollama --version
ollama version is 0.17.0

ollama run kimi-k2:1t-cloud
Error: ollama cloud is disabled: remote model details are unavailable
<!-- gh-comment-id:3967823973 --> @electroheadfx commented on GitHub (Feb 26, 2026): ```bash ollama --version ollama version is 0.17.0 ollama run kimi-k2:1t-cloud Error: ollama cloud is disabled: remote model details are unavailable ```
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#34249
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?