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 #2703] Ollama running on Xiaomi 13 Ultra #48128

New Issue
Closed
opened 2026-04-28 06:48:17 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 06:48:17 -05:00
Owner
Copy Link

Originally created by @lupo-ch on GitHub (Feb 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2703

Hello,
I'm running Ollama with Mistral:7B / Llama2:7B preinstalled and running locally on Xiaomi 13 Ultra smartphone which has 12 GB of RAM

I also tested it on my older Redmi Note 10 Pro with only 6GB of RAM. Here the smaller q3 version of Mistral:7B is working actually OK ...

The only one problem I had with this setup is that if I'm not communicating with the LLM for some time the ollama serve stops responding.

I have to exit the prompt with /bye and kill the PID of the ollama server and after restarting the service everything is working perfectly again ... :)
I'm starting the service on the Termux terminal with:
ollama serve > /dev/null 2>&1 &

On the link bellow I have made a detailed description of my setup, also I recorded 2 videos with the running Ollama setup on Xiaomi 13 Ultra (12GB) and Redmi Note 10 Pro (6GB):
https://thracium.net/Mistral-Mi13Ultra

Originally created by @lupo-ch on GitHub (Feb 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2703 Hello, I'm running Ollama with Mistral:7B / Llama2:7B preinstalled and running locally on Xiaomi 13 Ultra smartphone which has 12 GB of RAM I also tested it on my older Redmi Note 10 Pro with only 6GB of RAM. Here the smaller q3 version of Mistral:7B is working actually OK ... The only one problem I had with this setup is that if I'm not communicating with the LLM for some time the ollama serve stops responding. I have to exit the prompt with /bye and kill the PID of the ollama server and after restarting the service everything is working perfectly again ... :) I'm starting the service on the Termux terminal with: ollama serve > /dev/null 2>&1 & On the link bellow I have made a detailed description of my setup, also I recorded 2 videos with the running Ollama setup on Xiaomi 13 Ultra (12GB) and Redmi Note 10 Pro (6GB): https://thracium.net/Mistral-Mi13Ultra
GiteaMirror commented 2026-04-28 06:48:19 -05:00
Author
Owner
Copy Link

@mahone3297 commented on GitHub (Feb 23, 2024):

it looks like the behavior that OS make

<!-- gh-comment-id:1961460927 --> @mahone3297 commented on GitHub (Feb 23, 2024): it looks like the behavior that OS make
GiteaMirror commented 2026-04-28 06:48:19 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 10, 2024):

This should be fixed now (ollama serve hanging), however let me know if you're still seeing it

<!-- gh-comment-id:2103678108 --> @jmorganca commented on GitHub (May 10, 2024): This should be fixed now (`ollama serve` hanging), however let me know if you're still seeing it
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#48128
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?