github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10298] Support to GLM-Z1-32B, GLM-Z1-Rumination-32B #53275

New Issue
Closed
opened 2026-04-29 02:26:32 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-04-29 02:26:32 -05:00
Owner
Copy Link

Originally created by @sunisstar on GitHub (Apr 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10298

As title, gogogo!

Originally created by @sunisstar on GitHub (Apr 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10298 As title, gogogo!
GiteaMirror added the model label 2026-04-29 02:26:32 -05:00
GiteaMirror commented 2026-04-29 02:26:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 16, 2025):

#10269

<!-- gh-comment-id:2809711083 --> @rick-github commented on GitHub (Apr 16, 2025): #10269
GiteaMirror commented 2026-04-29 02:26:34 -05:00
Author
Owner
Copy Link

@lssac commented on GitHub (Apr 17, 2025):

+1

<!-- gh-comment-id:2812153950 --> @lssac commented on GitHub (Apr 17, 2025): +1
GiteaMirror commented 2026-04-29 02:26:35 -05:00
Author
Owner
Copy Link

@Circadian234 commented on GitHub (Apr 18, 2025):

These models are amazing for 32B! Please support

<!-- gh-comment-id:2814814921 --> @Circadian234 commented on GitHub (Apr 18, 2025): These models are amazing for 32B! Please support
GiteaMirror commented 2026-04-29 02:26:35 -05:00
Author
Owner
Copy Link

@mikestut commented on GitHub (Apr 18, 2025):

These models are amazing for 32B! Please support +1

<!-- gh-comment-id:2815658609 --> @mikestut commented on GitHub (Apr 18, 2025): These models are amazing for 32B! Please support +1
GiteaMirror commented 2026-04-29 02:26:35 -05:00
Author
Owner
Copy Link

@yujiaYY commented on GitHub (Apr 20, 2025):

These models are amazing for 32B! Please support

<!-- gh-comment-id:2817059318 --> @yujiaYY commented on GitHub (Apr 20, 2025): These models are amazing for 32B! Please support
GiteaMirror commented 2026-04-29 02:26:35 -05:00
Author
Owner
Copy Link

@Hunter6324 commented on GitHub (Apr 24, 2025):

go

<!-- gh-comment-id:2826127666 --> @Hunter6324 commented on GitHub (Apr 24, 2025): go
GiteaMirror commented 2026-04-29 02:26:36 -05:00
Author
Owner
Copy Link

@sunisstar commented on GitHub (Apr 24, 2025):

Good news, xinference has supported Z1 series after v1.5.0!
but I haven't tested it yet.

<!-- gh-comment-id:2828056141 --> @sunisstar commented on GitHub (Apr 24, 2025): Good news, xinference has supported Z1 series after v1.5.0! but I haven't tested it yet.
GiteaMirror commented 2026-04-29 02:26:37 -05:00
Author
Owner
Copy Link

@songsh commented on GitHub (Apr 28, 2025):

https://huggingface.co/bartowski/THUDM_GLM-Z1-32B-0414-GGUF/blob/main/THUDM_GLM-Z1-32B-0414-Q5_K_M.gguf
bartowski 出 z1-32b 模型，ollama 不支持。

<!-- gh-comment-id:2833720546 --> @songsh commented on GitHub (Apr 28, 2025): https://huggingface.co/bartowski/THUDM_GLM-Z1-32B-0414-GGUF/blob/main/THUDM_GLM-Z1-32B-0414-Q5_K_M.gguf bartowski 出 z1-32b 模型，ollama 不支持。
GiteaMirror commented 2026-04-29 02:26:40 -05:00
Author
Owner
Copy Link

@songsh commented on GitHub (Apr 28, 2025):

Good news, xinference has supported Z1 series after v1.5.0! but I haven't tested it yet.

i not found z1 support on xinference,

<!-- gh-comment-id:2833737512 --> @songsh commented on GitHub (Apr 28, 2025): > Good news, xinference has supported Z1 series after v1.5.0! but I haven't tested it yet. i not found z1 support on xinference,
GiteaMirror commented 2026-04-29 02:26:41 -05:00
Author
Owner
Copy Link

@mikestut commented on GitHub (Apr 28, 2025):

The model at https://ollama.com/JollyLlama/GLM-4-32B-0414-Q4_K_M has been extensively validated through testing and offers excellent performance for GLM4-32b implementation. So I strongly recommend downloading this optimized Q4_K_M quantized version for evaluation, particularly noting its improved inference speed while maintaining high accuracy. But please ensure your Ollama
version upgraded to v0.6.6+ before deployment, as this model requires specific tensor operations available only in the latest runtime. The combination of efficient memory usage
and robust natural language processing capabilities makes it an ideal choice for production-grade applications requiring large-scale language modeling.

<!-- gh-comment-id:2836974676 --> @mikestut commented on GitHub (Apr 28, 2025): The model at https://ollama.com/JollyLlama/GLM-4-32B-0414-Q4_K_M has been extensively validated through testing and offers excellent performance for GLM4-32b implementation. So I strongly recommend downloading this optimized Q4_K_M quantized version for evaluation, particularly noting its improved inference speed while maintaining high accuracy. But please ensure your Ollama version upgraded to **v0.6.6+** before deployment, as this model requires specific tensor operations available only in the latest runtime. The combination of efficient memory usage and robust natural language processing capabilities makes it an ideal choice for production-grade applications requiring large-scale language modeling.
GiteaMirror commented 2026-04-29 02:26:42 -05:00
Author
Owner
Copy Link

@limingchina commented on GitHub (May 11, 2025):

https://huggingface.co/bartowski/THUDM_GLM-Z1-32B-0414-GGUF/blob/main/THUDM_GLM-Z1-32B-0414-Q5_K_M.gguf bartowski 出 z1-32b 模型，ollama 不支持。

Tried this on LM Studio, I use the IQ_XS quant version from this page(https://huggingface.co/bartowski/THUDM_GLM-4-32B-0414-GGUF). Doesn't work. The output is competely garbage like this
/=::0")%H6'-'224&D16=-!0/935-A=7*(F713;>EF+(189-:B?&(E=?C!?#!F>)28?D"8148./"(A!4%"8+H#>3CFE!D<A&'>A)-2(5";5;(8:4E3C#"(:0>38"&(#7F3B-E68!$$>%;A4H.**C#-107/+2<B9D69157;'0'A%-A.>')4%8E1%6>

<!-- gh-comment-id:2870066053 --> @limingchina commented on GitHub (May 11, 2025): > https://huggingface.co/bartowski/THUDM_GLM-Z1-32B-0414-GGUF/blob/main/THUDM_GLM-Z1-32B-0414-Q5_K_M.gguf bartowski 出 z1-32b 模型，ollama 不支持。 Tried this on LM Studio, I use the IQ_XS quant version from this page(https://huggingface.co/bartowski/THUDM_GLM-4-32B-0414-GGUF). Doesn't work. The output is competely garbage like this `/=::0")%H6'-'224&D16=-!0/935-A=7*(F713;>EF+(189-:B?&(E=?C!?#!F>)28?D"8148./"(A!4%"8+H#>3CFE!D<A&'>A)-2(5";5;(8:4E3C#"(:0>38"&(#7F3B-E68!$$>%;A4H.**C#-107/+2<B9D69157;'0'A%-A.>')4%8E1%6> `
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#53275
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?