github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10190] llama vs ollama #6685

New Issue
Closed
opened 2026-04-12 18:24:50 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:24:50 -05:00
Owner
Copy Link

Originally created by @nigelzzz on GitHub (Apr 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10190

What is the issue?

Hi all,
recently, I tested llama.cpp (llama_cli) and ollama with llama3.2 q8 model, about prefill has some concern,

llama.cpp -> prefill : 2.5token/second
ollama -> prefill: 27 token/second

the ollama is faster than llama.cpp example, can i know the ollama have any improvement about prefill phase.
or is there any pull request can be reference?

Relevant log output

OS

Linux

GPU

No response

CPU

Other

Ollama version

No response

Originally created by @nigelzzz on GitHub (Apr 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10190 ### What is the issue? Hi all, recently, I tested llama.cpp (llama_cli) and ollama with llama3.2 q8 model, about prefill has some concern, llama.cpp -> prefill : 2.5token/second ollama -> prefill: 27 token/second the ollama is faster than llama.cpp example, can i know the ollama have any improvement about prefill phase. or is there any pull request can be reference? ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU Other ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 18:24:50 -05:00
GiteaMirror commented 2026-04-12 18:24:52 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 9, 2025):

Hi @nigelzzz

Thanks for sharing your findings — it’s always interesting to see performance comparisons across different tools like llama.cpp and Ollama.

That said, this doesn’t seem to describe a bug or issue specific to Ollama itself. From what I understand, it’s more of a general question about performance optimizations, which might be better suited for a conversation on Discord, where there’s more room for discussion and exchange with the community.

Just a suggestion: since the GitHub issue tracker is typically used for actionable bug reports or feature requests (especially with so many open issues here), you might consider closing this one if it doesn’t point to a specific problem.

<!-- gh-comment-id:2788285183 --> @igorschlum commented on GitHub (Apr 9, 2025): Hi @nigelzzz Thanks for sharing your findings — it’s always interesting to see performance comparisons across different tools like llama.cpp and Ollama. That said, this doesn’t seem to describe a bug or issue specific to Ollama itself. From what I understand, it’s more of a general question about performance optimizations, which might be better suited for a conversation on Discord, where there’s more room for discussion and exchange with the community. Just a suggestion: since the GitHub issue tracker is typically used for actionable bug reports or feature requests (especially with so many open issues here), you might consider closing this one if it doesn’t point to a specific problem.
GiteaMirror commented 2026-04-12 18:24:52 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 9, 2025):

@nigelzzz thank you!

<!-- gh-comment-id:2791181559 --> @igorschlum commented on GitHub (Apr 9, 2025): @nigelzzz thank you!
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#6685
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?