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 #3118] ollama RAM use on orangepi 5 #27678

New Issue
Closed
opened 2026-04-22 05:12:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 05:12:49 -05:00
Owner
Copy Link

Originally created by @parzzd on GitHub (Mar 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3118

Im trying model on my SBC, it has 16gb RAM, but the execution just uses 1.6gb, making the model take so much time to process.
Is there any parameter or configuration to allow it.
im new on Ollama, so any answer would be appreciated.

scr_proceso

times

Originally created by @parzzd on GitHub (Mar 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3118 Im trying model on my SBC, it has 16gb RAM, but the execution just uses 1.6gb, making the model take so much time to process. Is there any parameter or configuration to allow it. im new on Ollama, so any answer would be appreciated. ![scr_proceso](https://github.com/ollama/ollama/assets/103915075/5e43931c-9cb0-40d3-9f5f-975308db87aa) ![times](https://github.com/ollama/ollama/assets/103915075/57d9987a-0b99-4a6c-850b-5066b181619a)
GiteaMirror commented 2026-04-22 05:12:51 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Mar 13, 2024):

Hi there, I think in this case inference may be bound by your CPU (e.g. it has 50%+ utilization). May I ask which model you're running? Smaller models (e.g. gemma:2b, phi or tinyllama might run faster). Hope this helps!

<!-- gh-comment-id:1995249358 --> @jmorganca commented on GitHub (Mar 13, 2024): Hi there, I think in this case inference may be bound by your CPU (e.g. it has 50%+ utilization). May I ask which model you're running? Smaller models (e.g. `gemma:2b`, `phi` or `tinyllama` might run faster). Hope this helps!
GiteaMirror commented 2026-04-22 05:12:52 -05:00
Author
Owner
Copy Link

@parzzd commented on GitHub (Mar 13, 2024):

im ussing qwen1_5-4b-chat-q5_k_m.gguf

<!-- gh-comment-id:1995256476 --> @parzzd commented on GitHub (Mar 13, 2024): im ussing qwen1_5-4b-chat-q5_k_m.gguf
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#27678
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?