github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4843] Ollama running locally with very high latency #65100

New Issue
Closed
opened 2026-05-03 19:44:57 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 19:44:57 -05:00
Owner
Copy Link

Originally created by @vsatyakiran on GitHub (Jun 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4843

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I have installed ollama and tried to run llama2, llama3:8b but it is generating just 5 to 8 tokens per second , my system config: windows os, 16gb RAM
I also tried it on ec2 instance in aws with g5.xlarge instance type but facing the same latency, why it is happening?

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

0.1.39

Originally created by @vsatyakiran on GitHub (Jun 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4843 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I have installed ollama and tried to run llama2, llama3:8b but it is generating just 5 to 8 tokens per second , my system config: windows os, 16gb RAM I also tried it on ec2 instance in aws with g5.xlarge instance type but facing the same latency, why it is happening? ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version 0.1.39
GiteaMirror added the bugneeds more info labels 2026-05-03 19:44:58 -05:00
GiteaMirror commented 2026-05-03 19:45:01 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jun 6, 2024):

@vsatyakiran you're almost certainly running on the CPU instead of the GPU. What is the output of ollama ps? Also, what type of GPU are you trying to use? With the g5.xlarge I believe it's an a100 and there was an issue w/ nvidia driver version 555 which should be fixed in Ollama 0.1.40.

<!-- gh-comment-id:2153446291 --> @pdevine commented on GitHub (Jun 6, 2024): @vsatyakiran you're almost certainly running on the CPU instead of the GPU. What is the output of `ollama ps`? Also, what type of GPU are you trying to use? With the g5.xlarge I believe it's an a100 and there was an issue w/ nvidia driver version 555 which should be fixed in Ollama 0.1.40.
GiteaMirror commented 2026-05-03 19:45:02 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

@vsatyakiran if you're still having troubles, please upgrade to the latest version, and if that doesn't get you running on your GPU, please share your server log and I'll reopen the issue.

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md

<!-- gh-comment-id:2176985062 --> @dhiltgen commented on GitHub (Jun 18, 2024): @vsatyakiran if you're still having troubles, please upgrade to the latest version, and if that doesn't get you running on your GPU, please share your server log and I'll reopen the issue. https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md
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 needs more info
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#65100
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?