github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12910] [BUG] The qwen3-vl:30b-a3b-instruct model cannot output in parallel #34318

New Issue
Closed
opened 2026-04-22 17:46:00 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 17:46:00 -05:00
Owner
Copy Link

Originally created by @XiaZixun on GitHub (Nov 2, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12910

What is the issue?

I installed the Ollama service on my Mac via brew services start ollama and set OLLAMA_NUM_PARALLEL=4.

When using qwen3:4b-instruct or gemma3:27b-it-qat, the service performs parallel output normally.

However, when using qwen3-vl:30b-a3b-instruct, it always waits for one window's output to complete before the other window begins outputting.

Considering I have 64GB of GPU memory, and the qwen3-vl:30b-a3b-instruct model only has 20GB of weights, which is similar in size to gemma3:27b-it-qat, I don't think this is due to insufficient memory.

I haven't tested whether other Qwen3 VL models exhibit the same issue.

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.12.9

Originally created by @XiaZixun on GitHub (Nov 2, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12910 ### What is the issue? I installed the Ollama service on my Mac via `brew services start ollama` and set `OLLAMA_NUM_PARALLEL=4`. When using `qwen3:4b-instruct` or `gemma3:27b-it-qat`, the service performs parallel output normally. However, when using `qwen3-vl:30b-a3b-instruct`, it always waits for one window's output to complete before the other window begins outputting. Considering I have 64GB of GPU memory, and the `qwen3-vl:30b-a3b-instruct` model only has 20GB of weights, which is similar in size to `gemma3:27b-it-qat`, I don't think this is due to insufficient memory. I haven't tested whether other Qwen3 VL models exhibit the same issue. ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.12.9
GiteaMirror added the bug label 2026-04-22 17:46:00 -05:00
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#34318
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?