github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12854] Qwen3-VL Runs Significantly Slower Than Qwen2.5-VL on Windows with RTX 4090 #70578

New Issue
Closed
opened 2026-05-04 22:03:43 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-04 22:03:43 -05:00
Owner
Copy Link

Originally created by @yugame on GitHub (Oct 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12854

What is the issue?

qwen2.5vl:latest 5ced39dfa4ba 6.0 GB 35 minutes ago
qwen3-vl:latest 901cae732162 6.1 GB 56 minutes ago

I would like to report a bug: Ollama's Qwen3-VL runs abnormally slowly compared to Qwen2.5-VL. Environment: Windows with NVIDIA GeForce RTX 4090. Processing the same image takes only a few seconds with Qwen2.5-VL but tens of seconds with Qwen3-VL.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @yugame on GitHub (Oct 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12854 ### What is the issue? qwen2.5vl:latest 5ced39dfa4ba 6.0 GB 35 minutes ago qwen3-vl:latest 901cae732162 6.1 GB 56 minutes ago I would like to report a bug: Ollama's Qwen3-VL runs abnormally slowly compared to Qwen2.5-VL. Environment: Windows with NVIDIA GeForce RTX 4090. Processing the same image takes only a few seconds with Qwen2.5-VL but tens of seconds with Qwen3-VL. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 22:03:43 -05:00
GiteaMirror commented 2026-05-04 22:03:50 -05:00
Author
Owner
Copy Link

@yugame commented on GitHub (Oct 30, 2025):

ollama version is 0.12.7

<!-- gh-comment-id:3467014582 --> @yugame commented on GitHub (Oct 30, 2025): ollama version is 0.12.7
GiteaMirror commented 2026-05-04 22:03:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 30, 2025):

Server log may help in debugging.

<!-- gh-comment-id:3467052196 --> @rick-github commented on GitHub (Oct 30, 2025): [Server log](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.mdx) may help in debugging.
GiteaMirror commented 2026-05-04 22:03:54 -05:00
Author
Owner
Copy Link

@yugame commented on GitHub (Oct 30, 2025):

Maybe the ollama qwen3vl use thinking? This performance resembles using the program with Qwen/Qwen3-VL-8B-Thinking. If that's the case, could you provide the Qwen/Qwen3-VL-8B-Instruct model?

<!-- gh-comment-id:3467735070 --> @yugame commented on GitHub (Oct 30, 2025): Maybe the ollama qwen3vl use thinking? This performance resembles using the program with Qwen/Qwen3-VL-8B-Thinking. If that's the case, could you provide the Qwen/Qwen3-VL-8B-Instruct model?
GiteaMirror commented 2026-05-04 22:03:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 30, 2025):

https://ollama.com/library/qwen3-vl:8b-instruct

<!-- gh-comment-id:3467766128 --> @rick-github commented on GitHub (Oct 30, 2025): https://ollama.com/library/qwen3-vl:8b-instruct
GiteaMirror commented 2026-05-04 22:03:57 -05:00
Author
Owner
Copy Link

@yugame commented on GitHub (Oct 30, 2025):

thanks

<!-- gh-comment-id:3467786676 --> @yugame commented on GitHub (Oct 30, 2025): thanks
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#70578
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?