github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-22 12:05:47 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12627] Qwen 3 vl-30b request #8381

New Issue
Closed
opened 2026-04-12 21:01:36 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-12 21:01:36 -05:00
Owner
Copy Link
Copy Source

Originally created by @Jigit-ship-it on GitHub (Oct 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12627

Please add it for local using

Originally created by @Jigit-ship-it on GitHub (Oct 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12627 Please add it for local using
GiteaMirror added the model label 2026-04-12 21:01:36 -05:00
GiteaMirror commented 2026-04-12 21:01:37 -05:00
Author
Owner
Copy Link
Copy Source

@maternion commented on GitHub (Oct 15, 2025):

For now we only have qwen3-vl:235b-cloud, we have to wait for 235b, 30b and now 8b and 4b too. Let's see when we will get support.

<!-- gh-comment-id:3404684509 --> @maternion commented on GitHub (Oct 15, 2025): For now we only have qwen3-vl:235b-cloud, we have to wait for 235b, 30b and now 8b and 4b too. Let's see when we will get support.
GiteaMirror commented 2026-04-12 21:01:37 -05:00
Author
Owner
Copy Link
Copy Source

@drdaeman commented on GitHub (Oct 15, 2025):

Can someone please explain why there are cloud-only models? Right now, kimi-k2 and qwen3-vl are two models that only have a cloud tag variant, with no weights available - and I'm curious why.

<!-- gh-comment-id:3407783175 --> @drdaeman commented on GitHub (Oct 15, 2025): Can someone please explain why there are cloud-only models? Right now, `kimi-k2` and `qwen3-vl` are two models that only have a `cloud` tag variant, with no weights available - and I'm curious why.
GiteaMirror commented 2026-04-12 21:01:38 -05:00
Author
Owner
Copy Link
Copy Source

@maternion commented on GitHub (Oct 16, 2025):

Can someone please explain why there are cloud-only models? Right now, kimi-k2 and qwen3-vl are two models that only have a cloud tag variant, with no weights available - and I'm curious why.

Because maybe those larger models are easier to be deployed and tested on the cloud in comparison to adding them to the library and waiting for users to test them.

<!-- gh-comment-id:3410101813 --> @maternion commented on GitHub (Oct 16, 2025): > Can someone please explain why there are cloud-only models? Right now, `kimi-k2` and `qwen3-vl` are two models that only have a `cloud` tag variant, with no weights available - and I'm curious why. Because maybe those larger models are easier to be deployed and tested on the cloud in comparison to adding them to the library and waiting for users to test them.
GiteaMirror commented 2026-04-12 21:01:38 -05:00
Author
Owner
Copy Link
Copy Source

@maternion commented on GitHub (Oct 16, 2025):

https://github.com/ollama/ollama/issues/12397
Another issue is there, but for the 235b model which is currently on cloud.

<!-- gh-comment-id:3410105296 --> @maternion commented on GitHub (Oct 16, 2025): https://github.com/ollama/ollama/issues/12397 Another issue is there, but for the 235b model which is currently on cloud.
GiteaMirror commented 2026-04-12 21:01:38 -05:00
Author
Owner
Copy Link
Copy Source

@JohannesGaessler commented on GitHub (Oct 16, 2025):

Can someone please explain why there are cloud-only models? Right now, kimi-k2 and qwen3-vl are two models that only have a cloud tag variant, with no weights available - and I'm curious why.

Because they're not using ollama to run those models, most likely they're just forwarding user requests to e.g. deepinfra which runs vllm in the backend.

<!-- gh-comment-id:3413158223 --> @JohannesGaessler commented on GitHub (Oct 16, 2025): >Can someone please explain why there are cloud-only models? Right now, kimi-k2 and qwen3-vl are two models that only have a cloud tag variant, with no weights available - and I'm curious why. Because they're not using ollama to run those models, most likely they're just forwarding user requests to e.g. deepinfra which runs vllm in the backend.
GiteaMirror commented 2026-04-12 21:01:39 -05:00
Author
Owner
Copy Link
Copy Source

@drdaeman commented on GitHub (Oct 17, 2025):

most likely they're just forwarding user requests to e.g. deepinfra

I sincerely hope this is not the case. If Ollama Cloud runs anything on an infrastructure outside of Ollama control, there should be a proper disclosure.

And, uh, sorry about my comments being off-topic - I somehow confused 30b and 235b models.

<!-- gh-comment-id:3416504738 --> @drdaeman commented on GitHub (Oct 17, 2025): > most likely they're just forwarding user requests to e.g. deepinfra I sincerely hope this is not the case. If Ollama Cloud runs anything on an infrastructure outside of Ollama control, there should be a proper disclosure. And, uh, sorry about my comments being off-topic - I somehow confused 30b and 235b models.
GiteaMirror commented 2026-04-12 21:01:39 -05:00
Author
Owner
Copy Link
Copy Source

@maternion commented on GitHub (Oct 18, 2025):

I sincerely hope this is not the case. If Ollama Cloud runs anything on an infrastructure outside of Ollama control, there should be a proper disclosure.

As frob(contributor) mentioned in the Ollama discord, Cloud uses Ollama but not consumer ollama.

<!-- gh-comment-id:3417934655 --> @maternion commented on GitHub (Oct 18, 2025): > I sincerely hope this is not the case. If Ollama Cloud runs anything on an infrastructure outside of Ollama control, there should be a proper disclosure. As frob(contributor) mentioned in the Ollama discord, Cloud uses Ollama but not consumer ollama.
GiteaMirror commented 2026-04-12 21:01:40 -05:00
Author
Owner
Copy Link
Copy Source

@neiloliver4 commented on GitHub (Oct 25, 2025):

Ollama is going commercial, they dont care about local models. Move to Llama cpp.

<!-- gh-comment-id:3445859239 --> @neiloliver4 commented on GitHub (Oct 25, 2025): Ollama is going commercial, they dont care about local models. Move to Llama cpp.
GiteaMirror commented 2026-04-12 21:01:40 -05:00
Author
Owner
Copy Link
Copy Source

@rick-github commented on GitHub (Oct 29, 2025):

https://ollama.com/library/qwen3-vl:30b

<!-- gh-comment-id:3465187955 --> @rick-github commented on GitHub (Oct 29, 2025): https://ollama.com/library/qwen3-vl:30b
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 labels model
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8381