github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5056] qwen2 model error #3193

New Issue
Closed
opened 2026-04-12 13:41:13 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 13:41:13 -05:00
Owner
Copy Link

Originally created by @misi0202 on GitHub (Jun 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5056

What is the issue?

I'm try to use Qwen2-7b model by ollama(ollama run qwen2) , but meet timeout error by POST /api/compete, timed out occured.When I POST /api/chat,it can return reply error code like GGGGGGGGG, If the ollama don't support qwen2?

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @misi0202 on GitHub (Jun 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5056 ### What is the issue? I'm try to use Qwen2-7b model by ollama(ollama run qwen2) , but meet timeout error by POST /api/compete, timed out occured.When I POST /api/chat,it can return reply error code like GGGGGGGGG, If the ollama don't support qwen2? ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 13:41:13 -05:00
GiteaMirror commented 2026-04-12 13:41:15 -05:00
Author
Owner
Copy Link

@alwqx commented on GitHub (Jun 15, 2024):

Hi, Which ollama version you use? If the ollama version is < v0.1.42, you'd better upgrade to the latest ollama. This problem has been fixed in https://github.com/ollama/ollama/releases/tag/v0.1.42

refer https://github.com/ollama/ollama/issues/4907#issuecomment-2155671605

<!-- gh-comment-id:2169181924 --> @alwqx commented on GitHub (Jun 15, 2024): Hi, Which ollama version you use? If the ollama version is < v0.1.42, you'd better upgrade to the latest ollama. This problem has been fixed in https://github.com/ollama/ollama/releases/tag/v0.1.42 refer https://github.com/ollama/ollama/issues/4907#issuecomment-2155671605
GiteaMirror commented 2026-04-12 13:41:16 -05:00
Author
Owner
Copy Link

@misi0202 commented on GitHub (Jun 15, 2024):

Tks, I missed this question when I search, I will have a quick reply after updating Ollama.

<!-- gh-comment-id:2169190242 --> @misi0202 commented on GitHub (Jun 15, 2024): Tks, I missed this question when I search, I will have a quick reply after updating Ollama.
GiteaMirror commented 2026-04-12 13:41:17 -05:00
Author
Owner
Copy Link

@wgong commented on GitHub (Jun 15, 2024):

qwen2 works well now after updating Ollama, Thanks

<!-- gh-comment-id:2170249315 --> @wgong commented on GitHub (Jun 15, 2024): `qwen2` works well now after updating Ollama, Thanks
GiteaMirror commented 2026-04-12 13:41:17 -05:00
Author
Owner
Copy Link

@Speedway1 commented on GitHub (Jun 16, 2024):

What hardware are you running on ? I have seen that on my machine with 2 x AMD Radeon 7900 XTX cards, the 70B model puts out a load of GGGGGs or some other garbage, however on the smaller 7B model, it doesn't. However the 7B loads onto only 1 graphics card, not both.

This might be a fault in the AMD multi card usage. Llamacpp doesn't have this problem, runs perfectly. SO it's Ollama that seems to have this issue.

<!-- gh-comment-id:2171892511 --> @Speedway1 commented on GitHub (Jun 16, 2024): What hardware are you running on ? I have seen that on my machine with 2 x AMD Radeon 7900 XTX cards, the 70B model puts out a load of GGGGGs or some other garbage, however on the smaller 7B model, it doesn't. However the 7B loads onto only 1 graphics card, not both. This might be a fault in the AMD multi card usage. Llamacpp doesn't have this problem, runs perfectly. SO it's Ollama that seems to have this issue.
GiteaMirror commented 2026-04-12 13:41:17 -05:00
Author
Owner
Copy Link

@wgong commented on GitHub (Jun 17, 2024):

@Speedway1 I have 1 GPU (8GB vRAM)
image

<!-- gh-comment-id:2172033215 --> @wgong commented on GitHub (Jun 17, 2024): @Speedway1 I have 1 GPU (8GB vRAM) ![image](https://github.com/ollama/ollama/assets/329928/fe6d4812-1a37-4244-8374-8504b370d5e4)
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#3193
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?