github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10878] Ollama 0.7.1 shows a low performance than previous versions on Qwen 3 MoE model (30b-a3b) #7148

New Issue
Closed
opened 2026-04-12 19:09:02 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 19:09:02 -05:00
Owner
Copy Link

Originally created by @krpr on GitHub (May 27, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10878

What is the issue?

Image
Usage on version 0.7.1
Image
Usage on version 0.6.8 or 0.7.0 (sorry for my forgetting)

With the same hardware, Ollama 0.7.1 shows a low performance than 0.6.8 or 0.7.0 on Qwen 3 MoE model (30b-a3b)

OS: Ubuntu 24.04.2 LTS (GNU/Linux 6.8.0-60-generic x86_64)
CPU: AMD EPYC 7Y43 48-Core Processor x2
GPU: NVIDIA GeForce RTX 4090 48G x2

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.7.1

Originally created by @krpr on GitHub (May 27, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10878 ### What is the issue? ![Image](https://github.com/user-attachments/assets/5958b95a-751e-4686-ad67-8ec842591e38) Usage on version 0.7.1 ![Image](https://github.com/user-attachments/assets/a1fc74dc-0247-4aca-a851-0451dacfdf86) Usage on version 0.6.8 or 0.7.0 (sorry for my forgetting) With the same hardware, Ollama 0.7.1 shows a low performance than 0.6.8 or 0.7.0 on Qwen 3 MoE model (30b-a3b) OS: Ubuntu 24.04.2 LTS (GNU/Linux 6.8.0-60-generic x86_64) CPU: AMD EPYC 7Y43 48-Core Processor x2 GPU: NVIDIA GeForce RTX 4090 48G x2 ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.7.1
GiteaMirror added the needs more infobug labels 2026-04-12 19:09:02 -05:00
GiteaMirror commented 2026-04-12 19:09:03 -05:00
Author
Owner
Copy Link

@krpr commented on GitHub (May 27, 2025):

Image
even sometime the response token/s only 60% of the peak

<!-- gh-comment-id:2911685850 --> @krpr commented on GitHub (May 27, 2025): ![Image](https://github.com/user-attachments/assets/d9ac67af-0fc0-4588-86c4-4de107160b1e) even sometime the response token/s only 60% of the peak
GiteaMirror commented 2026-04-12 19:09:04 -05:00
Author
Owner
Copy Link

@frederikhendrix commented on GitHub (May 27, 2025):

Yes I have this as well. Also, when will ollama start running audio/transcription models?

<!-- gh-comment-id:2913797635 --> @frederikhendrix commented on GitHub (May 27, 2025): Yes I have this as well. Also, when will ollama start running audio/transcription models?
GiteaMirror commented 2026-04-12 19:09:04 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 10, 2025):

Server logs may help in debugging.

<!-- gh-comment-id:2958397095 --> @rick-github commented on GitHub (Jun 10, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may help in debugging.
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 needs more info
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#7148
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?