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 #12541] gpt-oss:20b is slower and slow #70381

New Issue
Open
opened 2026-05-04 21:21:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 21:21:42 -05:00
Owner
Copy Link

Originally created by @mitar on GitHub (Oct 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12541

What is the issue?

I use a set of tests which run against a model. I run them on only-CPU GitLab shared runner of type saas-linux-2xlarge-amd64 (32 vCPUs, 128 GB memory).

I was evaluating gpt-oss:20b and tests took much longer than llama3.1:70b. See example log: https://gitlab.com/tozd/go/fun/-/jobs/11651913043 There are completions taking 50+ minutes. (Whole CI job has 3 hours timeout.) So it looks like everything gets very slow sometimes.

Same tests on llama3.1:70b finish in 20 minutes total CI job time, without such drastic growing of chat completion times: https://gitlab.com/tozd/go/fun/-/jobs/11652542853

Relevant log output

OS

Linux, Docker

GPU

No response

CPU

Intel

Ollama version

0.12.3

Originally created by @mitar on GitHub (Oct 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12541 ### What is the issue? I use a set of tests which run against a model. I run them on only-CPU GitLab shared runner of type `saas-linux-2xlarge-amd64` (32 vCPUs, 128 GB memory). I was evaluating gpt-oss:20b and tests took much longer than llama3.1:70b. See example log: https://gitlab.com/tozd/go/fun/-/jobs/11651913043 There are completions taking 50+ minutes. (Whole CI job has 3 hours timeout.) So it looks like everything gets very slow sometimes. Same tests on llama3.1:70b finish in 20 minutes total CI job time, without such drastic growing of chat completion times: https://gitlab.com/tozd/go/fun/-/jobs/11652542853 ### Relevant log output ```shell ``` ### OS Linux, Docker ### GPU _No response_ ### CPU Intel ### Ollama version 0.12.3
GiteaMirror added the bug label 2026-05-04 21:21:42 -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#70381
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?