github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10746] Gemma3:27b slow using 0.7.0 #69118

New Issue
Closed
opened 2026-05-04 17:13:06 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 17:13:06 -05:00
Owner
Copy Link

Originally created by @jarek7777 on GitHub (May 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10746

What is the issue?

Version 0.7.0 is 3 times slower compared to 0.6.8 using gemma3:27b-it-qat
Ubuntu, AMD, nVidia 3090

0.7.0:
eval count: 74 token(s)
eval duration: 5.657106746s
eval rate: 13.08 tokens/s

0.6.8:
eval count: 63 token(s)
eval duration: 1.748827692s
eval rate: 36.02 tokens/s

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.7.0

Originally created by @jarek7777 on GitHub (May 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10746 ### What is the issue? Version 0.7.0 is 3 times slower compared to 0.6.8 using **gemma3:27b-it-qat** _Ubuntu, AMD, nVidia 3090_ **0.7.0:** eval count: 74 token(s) eval duration: 5.657106746s eval rate: **13.08 tokens/s** **0.6.8:** eval count: 63 token(s) eval duration: 1.748827692s eval rate: **36.02 tokens/s** ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.7.0
GiteaMirror added the bug label 2026-05-04 17:13:06 -05:00
GiteaMirror commented 2026-05-04 17:13:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 16, 2025):

Server logs may aid in debugging.

<!-- gh-comment-id:2887410977 --> @rick-github commented on GitHub (May 16, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.
GiteaMirror commented 2026-05-04 17:13:15 -05:00
Author
Owner
Copy Link

@jarek7777 commented on GitHub (May 16, 2025):

Ok this is due to the default Ollama VRAM requirements, so maybe is not an issue?
0.7.0: gemma3:27b-it-qat 29eb0b9aeda3 25 GB 11%/89% CPU/GPU 4 minutes from now
0.6.8: gemma3:27b-it-qat 29eb0b9aeda3 22 GB 100% GPU 4 minutes from now

<!-- gh-comment-id:2887427691 --> @jarek7777 commented on GitHub (May 16, 2025): Ok this is due to the default Ollama VRAM requirements, so maybe is not an issue? 0.7.0: gemma3:27b-it-qat 29eb0b9aeda3 25 GB 11%/89% CPU/GPU 4 minutes from now 0.6.8: gemma3:27b-it-qat 29eb0b9aeda3 22 GB 100% GPU 4 minutes from now
GiteaMirror commented 2026-05-04 17:13:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 16, 2025):

#10726

<!-- gh-comment-id:2887431858 --> @rick-github commented on GitHub (May 16, 2025): #10726
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#69118
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?