Imported from https://hf.co/unsloth/GLM-5.3-GGUF.

Chat/thinking

The model template doesn’t have a way to disable thinking. It supports reasoning levels of low, high and max, with max being the default.

$ ollama run frob/glm-5.3
>>> hello
Thinking...
Let me consider how to respond to this greeting thoughtfully.

The user has started with a simple "hello" - this is likely the beginning 
of a conversation. I should respond in a way that's both welcoming and 
open-ended.

First, I'll acknowledge their greeting warmly. Then I should introduce 
myself briefly to establish context. Since this is an initial interaction, 
I should also express my willingness to help while inviting them to share 
what's on their mind.

I need to make sure my response feels natural and conversational, not 
overly formal or robotic. It would be good to end with an open question 
that encourages them to continue the dialogue.

The key is to create a friendly atmosphere where they feel comfortable 
sharing what they need assistance with. This initial exchange sets the tone 
for our entire conversation, so it's important to get it right.

Let me craft a response that's welcoming, informative, and encourages 
further conversation.
...done thinking.

Hello! I'm GLM, trained by Z.ai. Nice to meet you, and I hope you're having 
a great day.

Do you have any questions or topics of interest I can help you with? I’m 
happy to assist you.

Tools

$ ollama launch opencode \
    --model frob/glm-5.3 \
    -- \
    run 'create a file called README with the contents "hello world"'

> build · frob/glm-5.3:latest

← Write README
Wrote file successfully.

Created `README` with "hello world".

$ cat README
hello world