github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #121] Performance question? #42

New Issue
Closed
opened 2026-04-12 09:34:32 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 09:34:32 -05:00
Owner
Copy Link

Originally created by @kosecki123 on GitHub (Jul 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/121

This is just request for info rather than a bug.

What's kind of performance / latency on prompts we should expect running on M2 Pro ? Seems like takes up to 10s to generate the answers using llama2 model. Is that something that can improve in the future?

Originally created by @kosecki123 on GitHub (Jul 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/121 This is just request for info rather than a bug. What's kind of performance / latency on prompts we should expect running on M2 Pro ? Seems like takes up to 10s to generate the answers using `llama2` model. Is that something that can improve in the future?
GiteaMirror commented 2026-04-12 09:34:35 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 19, 2023):

Hi @kosecki123 . Absolutely. That 10 seconds is loading in the model, and we're working on making that much shorter!

Thanks for the issue!

<!-- gh-comment-id:1641632393 --> @jmorganca commented on GitHub (Jul 19, 2023): Hi @kosecki123 . Absolutely. That 10 seconds is loading in the model, and we're working on making that much shorter! Thanks for the issue!
GiteaMirror commented 2026-04-12 09:34:35 -05:00
Author
Owner
Copy Link

@zhiyun-deng commented on GitHub (Jul 29, 2023):

Why not keep the model loaded in between prompts? Providing such option would make the user experience much smoother.

<!-- gh-comment-id:1656656538 --> @zhiyun-deng commented on GitHub (Jul 29, 2023): Why not keep the model loaded in between prompts? Providing such option would make the user experience much smoother.
GiteaMirror commented 2026-04-12 09:34:36 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 30, 2023):

@zhiyun-deng 💯 – the next release will do this! You can also test this out on main

<!-- gh-comment-id:1657001868 --> @jmorganca commented on GitHub (Jul 30, 2023): @zhiyun-deng 💯 – the next release will do this! You can also test this out on `main`
GiteaMirror commented 2026-04-12 09:34:36 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Aug 23, 2023):

Closing for now as the same model will stay loaded between prompts

<!-- gh-comment-id:1690377788 --> @jmorganca commented on GitHub (Aug 23, 2023): Closing for now as the same model will stay loaded between prompts
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
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#42
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?