github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2742] How to improve ollama performance #63688

New Issue
Closed
opened 2026-05-03 14:40:52 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 14:40:52 -05:00
Owner
Copy Link

Originally created by @gautam-fairpe on GitHub (Feb 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2742

Originally assigned to: @dhiltgen on GitHub.

current model params :
FROM llama2:13b-chat
PARAMETER temperature 0.2
PARAMETER num_ctx 4096
PARAMETER num_thread 16
PARAMETER use_mmap False

System config :
Ram 108 GB
T4 graphics card 16 gb
Screenshot from 2024-02-25 17-57-04

Also hardly any ram is being used.
Using ollama python bindings to get the result but due to some params issue not getting the result as expected. What am i missing here ?

Originally created by @gautam-fairpe on GitHub (Feb 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2742 Originally assigned to: @dhiltgen on GitHub. current model params : FROM llama2:13b-chat PARAMETER temperature 0.2 PARAMETER num_ctx 4096 PARAMETER num_thread 16 PARAMETER use_mmap False System config : Ram 108 GB T4 graphics card 16 gb ![Screenshot from 2024-02-25 17-57-04](https://github.com/ollama/ollama/assets/127822235/24854715-93b3-4732-9b6f-bd1a373a9417) Also hardly any ram is being used. Using ollama python bindings to get the result but due to some params issue not getting the result as expected. What am i missing here ?
GiteaMirror added the performancenvidia labels 2026-05-03 14:40:53 -05:00
GiteaMirror commented 2026-05-03 14:41:04 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Feb 25, 2024):

Look in the log file to see what it says about GPU detection and model layers being offloaded to GPU

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues

<!-- gh-comment-id:1963006601 --> @easp commented on GitHub (Feb 25, 2024): Look in the log file to see what it says about GPU detection and model layers being offloaded to GPU https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues
GiteaMirror commented 2026-05-03 14:41:08 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 11, 2024):

If you're still having performance problems, please share your server log so we can better understand what's going wrong.

(also please make sure to upgrade to the latest version in case a bug fix resolves the problem)

<!-- gh-comment-id:1989466317 --> @dhiltgen commented on GitHub (Mar 11, 2024): If you're still having performance problems, please share your server log so we can better understand what's going wrong. (also please make sure to upgrade to the latest version in case a bug fix resolves the problem)
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 nvidia performance
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#63688
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?