github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14795] Ollama API error 400: {"error":"registry.ollama.ai/library/Qwen3.5:0.8b does not support tools"} #35316

New Issue
Closed
opened 2026-04-22 19:45:25 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 19:45:25 -05:00
Owner
Copy Link

Originally created by @LMingJian on GitHub (Mar 12, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14795

What is the issue?

I download Qwen3.5:0.8b from HuggingFace. and then, I executed the following command to create the model.

ollama create qwen3.5:0.8b

When I use OpenClaw, OpenClaw cannot call the Ollama model interface, and the interface reports an error

Ollama API error 400: {"error":"registry.ollama.ai/library/Qwen3.5:0.8b does not support tools"}

But on the official website, Qwen3.5:0.8b supports tools

Image

Why is this happening, please tell me the reason, thank you very much.

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.17.7

Originally created by @LMingJian on GitHub (Mar 12, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14795 ### What is the issue? I download [Qwen3.5:0.8b](https://huggingface.co/Qwen/Qwen3.5-0.8B) from HuggingFace. and then, I executed the following command to create the model. ``` ollama create qwen3.5:0.8b ``` When I use OpenClaw, OpenClaw cannot call the Ollama model interface, and the interface reports an error ``` Ollama API error 400: {"error":"registry.ollama.ai/library/Qwen3.5:0.8b does not support tools"} ``` But on the official website, Qwen3.5:0.8b supports tools <img width="990" height="353" alt="Image" src="https://github.com/user-attachments/assets/c6a221ab-c344-4c45-ae99-1ed17757ea68" /> Why is this happening, please tell me the reason, thank you very much. ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.17.7
GiteaMirror added the bug label 2026-04-22 19:45:25 -05:00
GiteaMirror commented 2026-04-22 19:45:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 12, 2026):

You need to merge the template from the ollama model with the model downloaded from HF. But why not use the model from the ollama library?

<!-- gh-comment-id:4047007808 --> @rick-github commented on GitHub (Mar 12, 2026): You need to merge the template from the ollama model with the model downloaded from HF. But why not use the model from the ollama library?
GiteaMirror commented 2026-04-22 19:45:30 -05:00
Author
Owner
Copy Link

@LMingJian commented on GitHub (Mar 13, 2026):

You are right, I successfully used it after setting TEMPLATE in the ModelFile.
There is a chat_template.jinja file in Qwen3.5's folder, but, ollama does not support Jinja template files.
I cannot directly copy the contents of the jinja file into the ModelFile. And, I can't find a way to convert jinja files into templates supported by ollama.
In the end, I could only find the template in the official documentation, https://qwen.readthedocs.io/zh-cn/stable/run_locally/ollama.html
I think Ollama should provide support for Jinja template files.
Finally, thank you for your suggestion.

why not use the model from the ollama library? I live in China, So downloading models from Ollama CLI is very slow, but I have a way to normally download models from HF website

<!-- gh-comment-id:4051916382 --> @LMingJian commented on GitHub (Mar 13, 2026): You are right, I successfully used it after setting TEMPLATE in the ModelFile. There is a chat_template.jinja file in Qwen3.5's folder, but, ollama does not support Jinja template files. I cannot directly copy the contents of the jinja file into the ModelFile. And, I can't find a way to convert jinja files into templates supported by ollama. In the end, I could only find the template in the official documentation, https://qwen.readthedocs.io/zh-cn/stable/run_locally/ollama.html I think Ollama should provide support for Jinja template files. Finally, thank you for your suggestion. > why not use the model from the ollama library? I live in China, So downloading models from Ollama CLI is very slow, but I have a way to normally download models from HF website
GiteaMirror commented 2026-04-22 19:45:31 -05:00
Author
Owner
Copy Link

@oldhare1024 commented on GitHub (Mar 13, 2026):

I meet this question too

<!-- gh-comment-id:4052082082 --> @oldhare1024 commented on GitHub (Mar 13, 2026): I meet this question too
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#35316
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?