github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5553] GLM4-1m support #29231

New Issue
Open
opened 2026-04-22 07:56:33 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 07:56:33 -05:00
Owner
Copy Link

Originally created by @taozhiyuai on GitHub (Jul 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5553

What is the issue?

taozhiyu@603e5f4a42f1 downloads % ollama run glm4:9b-chat-1m-q8_0
pulling manifest
pulling 5c0b5b35f3e0... 100% ▕█████████████████▏ 10 GB
pulling e7e7aebd710c... 100% ▕█████████████████▏ 137 B
pulling e4f0dc83900a... 100% ▕█████████████████▏ 6.5 KB
pulling 4134f3eb0516... 100% ▕█████████████████▏ 81 B
pulling dcddad887d90... 100% ▕█████████████████▏ 489 B
verifying sha256 digest
writing manifest
removing any unused layers
success
Error: llama runner process has terminated: signal: abort trap error:check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected 4096, 4608, got 4096, 5120, 1, 1

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.2

Originally created by @taozhiyuai on GitHub (Jul 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5553 ### What is the issue? taozhiyu@603e5f4a42f1 downloads % ollama run glm4:9b-chat-1m-q8_0 pulling manifest pulling 5c0b5b35f3e0... 100% ▕█████████████████▏ 10 GB pulling e7e7aebd710c... 100% ▕█████████████████▏ 137 B pulling e4f0dc83900a... 100% ▕█████████████████▏ 6.5 KB pulling 4134f3eb0516... 100% ▕█████████████████▏ 81 B pulling dcddad887d90... 100% ▕█████████████████▏ 489 B verifying sha256 digest writing manifest removing any unused layers success Error: llama runner process has terminated: signal: abort trap error:check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected 4096, 4608, got 4096, 5120, 1, 1 ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.2
GiteaMirror added the model label 2026-04-22 07:56:33 -05:00
GiteaMirror commented 2026-04-22 07:56:34 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (Jul 9, 2024):

taozhiyu@603e5f4a42f1 ~ % ollama --version
ollama version is 0.2.0
taozhiyu@603e5f4a42f1 ~ % ollama run glm4:9b-chat-1m-q8_0
Error: llama runner process has terminated: signal: abort trap error:check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected 4096, 4608, got 4096, 5120, 1, 1

<!-- gh-comment-id:2216166309 --> @taozhiyuai commented on GitHub (Jul 9, 2024): taozhiyu@603e5f4a42f1 ~ % ollama --version ollama version is 0.2.0 taozhiyu@603e5f4a42f1 ~ % ollama run glm4:9b-chat-1m-q8_0 Error: llama runner process has terminated: signal: abort trap error:check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected 4096, 4608, got 4096, 5120, 1, 1
GiteaMirror commented 2026-04-22 07:56:35 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 9, 2024):

Hi @taozhiyuai sorry about that, the 1m model isn't yet supported – will work on making this happen

<!-- gh-comment-id:2216241740 --> @jmorganca commented on GitHub (Jul 9, 2024): Hi @taozhiyuai sorry about that, the 1m model isn't yet supported – will work on making this happen
GiteaMirror commented 2026-04-22 07:56:35 -05:00
Author
Owner
Copy Link

@VarLad commented on GitHub (Jul 9, 2024):

@jmorganca Any plans to support the GLM4V-9B model?

<!-- gh-comment-id:2217924361 --> @VarLad commented on GitHub (Jul 9, 2024): @jmorganca Any plans to support the GLM4V-9B model?
GiteaMirror commented 2026-04-22 07:56:36 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 10, 2024):

@VarLad you can ollama run glm4. Make sure you've updated to the latest release. I will default to the 9B model.

<!-- gh-comment-id:2221131452 --> @pdevine commented on GitHub (Jul 10, 2024): @VarLad you can `ollama run glm4`. Make sure you've updated to the latest release. I will default to the 9B model.
GiteaMirror commented 2026-04-22 07:56:36 -05:00
Author
Owner
Copy Link

@VarLad commented on GitHub (Jul 11, 2024):

@pdevine I get

Error: llama runner process has terminated: signal: aborted (core dumped) error:failed to create context with model '~/.ollama/models/blobs/sha256-b506a070d1152798d435ec4e7687336567ae653b3106f73b7b4ac7be1cbc4449

when I run:
ollama run glm4

This is for version 0.2.1

<!-- gh-comment-id:2222366048 --> @VarLad commented on GitHub (Jul 11, 2024): @pdevine I get ``` Error: llama runner process has terminated: signal: aborted (core dumped) error:failed to create context with model '~/.ollama/models/blobs/sha256-b506a070d1152798d435ec4e7687336567ae653b3106f73b7b4ac7be1cbc4449 ``` when I run: `ollama run glm4` This is for version 0.2.1
GiteaMirror commented 2026-04-22 07:56:37 -05:00
Author
Owner
Copy Link

@VarLad commented on GitHub (Jul 11, 2024):

Also, that being an issue with itself, I was inquiring about the https://huggingface.co/THUDM/glm-4v-9b model which is a vision model and part of the GLM4 family.
I do believe that ollama supports vision models like LLAVA (correct?)

<!-- gh-comment-id:2222371702 --> @VarLad commented on GitHub (Jul 11, 2024): Also, that being an issue with itself, I was inquiring about the https://huggingface.co/THUDM/glm-4v-9b model which is a vision model and part of the GLM4 family. I do believe that ollama supports vision models like LLAVA (correct?)
GiteaMirror commented 2026-04-22 07:56:37 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 11, 2024):

@VarLad there was a problem with the graph for calculating how much memory is being used. There's a fix for that coming out in 0.2.2 which is coming out imminently. The glm-4v isn't supported yet.

<!-- gh-comment-id:2223526070 --> @pdevine commented on GitHub (Jul 11, 2024): @VarLad there was a problem with the graph for calculating how much memory is being used. There's a fix for that coming out in 0.2.2 which is coming out imminently. The glm-4v isn't supported yet.
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#29231
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?