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 #11564] Support for zai-org/GLM-4.5-Air (Thinking & Non-Thinking Modes + Tool Use) #69691

New Issue
Closed
opened 2026-05-04 18:51:16 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 18:51:16 -05:00
Owner
Copy Link

Originally created by @zytoh0 on GitHub (Jul 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11564

Hi team,
Please consider adding support for the zai-org/GLM-4.5-Air model and its FP8 variant zai-org/GLM-4.5-Air-FP8. These models are designed for hybrid reasoning and support:

  • Thinking mode: for complex reasoning and tool usage

  • Non-thinking mode: for quick, direct responses

The Air variant is optimized for lightweight deployment, and the FP8 version further enhances efficiency. Supporting both modes and tool use functionality would make these models highly versatile for a wide range of environments.

Appreciate your consideration!

Originally created by @zytoh0 on GitHub (Jul 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11564 Hi team, Please consider adding support for the [zai-org/GLM-4.5-Air](https://huggingface.co/zai-org/GLM-4.5-Air) model and its FP8 variant [zai-org/GLM-4.5-Air-FP8](https://huggingface.co/zai-org/GLM-4.5-Air-FP8). These models are designed for hybrid reasoning and support: - **Thinking mode**: for complex reasoning and tool usage - **Non-thinking mode**: for quick, direct responses The Air variant is optimized for lightweight deployment, and the FP8 version further enhances efficiency. Supporting both modes and **tool use functionality** would make these models highly versatile for a wide range of environments. Appreciate your consideration!
GiteaMirror added the model label 2026-05-04 18:51:16 -05:00
GiteaMirror commented 2026-05-04 18:51:23 -05:00
Author
Owner
Copy Link

@zytoh0 commented on GitHub (Aug 2, 2025):

@rick-github This is not a duplicate of Support for zai-org/GLM-4.5 (Thinking & Non-Thinking Modes + Tool Use) #11563, as this issue concerns the Air variant - GLM-4.5-Air - which is a distinct and significantly smaller model compared to the standard GLM-4.5 (106B vs 355B total parameters; 12B vs 32B active parameters). The two versions offer different trade-offs in performance and efficiency, similar to how both phi-4 and phi-4-mini are included separately in Ollama. Given these substantial differences, this request should be tracked independently. Kindly consider reopening this issue.

<!-- gh-comment-id:3146549293 --> @zytoh0 commented on GitHub (Aug 2, 2025): @rick-github This is not a [duplicate](https://github.com/ollama/ollama/issues?q=is%3Aissue+state%3Aclosed+archived%3Afalse+reason%3Aduplicate) of [Support for zai-org/GLM-4.5 (Thinking & Non-Thinking Modes + Tool Use) #11563](https://github.com/ollama/ollama/issues/11563), as this issue concerns the Air variant - GLM-4.5-Air - which is a distinct and significantly smaller model compared to the standard GLM-4.5 (106B vs 355B total parameters; 12B vs 32B active parameters). The two versions offer different trade-offs in performance and efficiency, similar to how both phi-4 and phi-4-mini are included separately in Ollama. Given these substantial differences, this request should be tracked independently. Kindly consider reopening this issue.
GiteaMirror commented 2026-05-04 18:51:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 2, 2025):

The model architecture is the same.

<!-- gh-comment-id:3146561723 --> @rick-github commented on GitHub (Aug 2, 2025): The model architecture is the same.
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 model
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#69691
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?