github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-11-13 17:34:40 -06:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12645] glm-4.6 cloud name breaks some clients. #8394

New Issue
Closed
opened 2026-04-12 21:02:33 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 21:02:33 -05:00
Owner
Copy Link
Copy Source

Originally created by @rick-github on GitHub (Oct 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12645

What is the issue?

Dropping the tag from glm-4.6 in Cloud makes it impossible to some clients to use the model via direct connection. The (unspoken?) rule to date has been that if an ollama model doesn't have a tag, then appending ":latest" is an appropriate action. Unfortunately, this prevents (for example) OpenWebUI from calling the model, since the Cloud server can't find "glm-4.6:latest".

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @rick-github on GitHub (Oct 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12645 ### What is the issue? Dropping the tag from glm-4.6 in Cloud makes it impossible to some clients to use the model via direct connection. The (unspoken?) rule to date has been that if an ollama model doesn't have a tag, then appending ":latest" is an appropriate action. Unfortunately, this prevents (for example) OpenWebUI from calling the model, since the Cloud server can't find "glm-4.6:latest". ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the cloudbug labels 2026-04-12 21:02:33 -05:00
GiteaMirror commented 2026-04-12 21:02:35 -05:00
Author
Owner
Copy Link
Copy Source

@gattytto commented on GitHub (Oct 15, 2025):

adding ollama.com as provider directly to open-webui breaks glm-4.6
Image

<!-- gh-comment-id:3408591965 --> @gattytto commented on GitHub (Oct 15, 2025): adding ollama.com as provider directly to open-webui breaks glm-4.6 <img width="1360" height="363" alt="Image" src="https://github.com/user-attachments/assets/45c60dd7-64d8-4dd8-9a25-aad4437c07ac" />
GiteaMirror commented 2026-04-12 21:02:35 -05:00
Author
Owner
Copy Link
Copy Source

@jmorganca commented on GitHub (Oct 15, 2025):

@rick-github thanks for the issue! A fix for this is going out right now. Let me know if you still see it!

<!-- gh-comment-id:3408653147 --> @jmorganca commented on GitHub (Oct 15, 2025): @rick-github thanks for the issue! A fix for this is going out right now. Let me know if you still see it!
GiteaMirror commented 2026-04-12 21:02:35 -05:00
Author
Owner
Copy Link
Copy Source

@JakubMrowicki commented on GitHub (Oct 26, 2025):

Looks like this is still a problem as ":latest" is always appended to models where no tag is present. In this case "glm-4.6" is the full name in https://ollama.com/api/tags and so :latest is appended, causing the 400.

<!-- gh-comment-id:3448728661 --> @JakubMrowicki commented on GitHub (Oct 26, 2025): Looks like this is still a problem as ":latest" is always appended to models where no tag is present. In this case "glm-4.6" is the full name in https://ollama.com/api/tags and so :latest is appended, causing the 400.
GiteaMirror commented 2026-04-12 21:02:36 -05:00
Author
Owner
Copy Link
Copy Source

@rick-github commented on GitHub (Oct 26, 2025):

$ date
Sun Oct 26 06:50:44 PM CET 2025
$ OLLAMA_HOST=ollama.com ollama run glm-4.6:latest hello
Thinking...
Let me consider how to respond to this greeting thoughtfully.
...
<!-- gh-comment-id:3448730032 --> @rick-github commented on GitHub (Oct 26, 2025): ```console $ date Sun Oct 26 06:50:44 PM CET 2025 $ OLLAMA_HOST=ollama.com ollama run glm-4.6:latest hello Thinking... Let me consider how to respond to this greeting thoughtfully. ... ```
GiteaMirror commented 2026-04-12 21:02:37 -05:00
Author
Owner
Copy Link
Copy Source

@JakubMrowicki commented on GitHub (Oct 26, 2025):

This resolves it for CLI, but not API endpoints.
https://docs.ollama.com/api#model-names

"Model names follow a model:tag format, where model can have an optional namespace such as example/model. Some examples are orca-mini:3b-q4_1 and llama3:70b. The tag is optional and, if not provided, will default to latest. The tag is used to identify a specific version."

So my issue when using this using open-webui persists.

{
  "models": [
    {
      "name": "glm-4.6",
      "model": "glm-4.6",
      "modified_at": "2025-09-29T00:00:00Z",
      "size": 696060000000,
      "digest": "ee0873722cc3",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "kimi-k2:1t",
      "model": "kimi-k2:1t",
      "modified_at": "2025-09-05T00:00:00Z",
      "size": 1118481408000,
      "digest": "7bb8dfabfd9c",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "qwen3-coder:480b",
      "model": "qwen3-coder:480b",
      "modified_at": "2025-07-22T00:00:00Z",
      "size": 510492157952,
      "digest": "653ca2ec1d71",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "deepseek-v3.1:671b",
      "model": "deepseek-v3.1:671b",
      "modified_at": "2025-08-21T00:00:00Z",
      "size": 688586727753,
      "digest": "e1c8a9725f49",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "gpt-oss:120b",
      "model": "gpt-oss:120b",
      "modified_at": "2025-08-05T00:00:00Z",
      "size": 65290180781,
      "digest": "d98fe6ba01e6",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "gpt-oss:20b",
      "model": "gpt-oss:20b",
      "modified_at": "2025-08-05T00:00:00Z",
      "size": 13780162412,
      "digest": "05afbac4bad6",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    },
    {
      "name": "qwen3-vl:235b",
      "model": "qwen3-vl:235b",
      "modified_at": "2025-09-22T00:00:00Z",
      "size": 237000000000,
      "digest": "a5020f0cea71",
      "details": {
        "parent_model": "",
        "format": "",
        "family": "",
        "families": null,
        "parameter_size": "",
        "quantization_level": ""
      }
    }
  ]
}
<!-- gh-comment-id:3448754617 --> @JakubMrowicki commented on GitHub (Oct 26, 2025): This resolves it for CLI, but not API endpoints. https://docs.ollama.com/api#model-names "Model names follow a model:tag format, where model can have an optional namespace such as example/model. Some examples are orca-mini:3b-q4_1 and llama3:70b. The tag is optional and, if not provided, will default to latest. The tag is used to identify a specific version." So my issue when using this using open-webui persists. ``` { "models": [ { "name": "glm-4.6", "model": "glm-4.6", "modified_at": "2025-09-29T00:00:00Z", "size": 696060000000, "digest": "ee0873722cc3", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "kimi-k2:1t", "model": "kimi-k2:1t", "modified_at": "2025-09-05T00:00:00Z", "size": 1118481408000, "digest": "7bb8dfabfd9c", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "qwen3-coder:480b", "model": "qwen3-coder:480b", "modified_at": "2025-07-22T00:00:00Z", "size": 510492157952, "digest": "653ca2ec1d71", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "deepseek-v3.1:671b", "model": "deepseek-v3.1:671b", "modified_at": "2025-08-21T00:00:00Z", "size": 688586727753, "digest": "e1c8a9725f49", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "gpt-oss:120b", "model": "gpt-oss:120b", "modified_at": "2025-08-05T00:00:00Z", "size": 65290180781, "digest": "d98fe6ba01e6", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "gpt-oss:20b", "model": "gpt-oss:20b", "modified_at": "2025-08-05T00:00:00Z", "size": 13780162412, "digest": "05afbac4bad6", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } }, { "name": "qwen3-vl:235b", "model": "qwen3-vl:235b", "modified_at": "2025-09-22T00:00:00Z", "size": 237000000000, "digest": "a5020f0cea71", "details": { "parent_model": "", "format": "", "family": "", "families": null, "parameter_size": "", "quantization_level": "" } } ] } ```
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 labels bug cloud
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8394