github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1752] Ollama can run in Docker (hosted in local machine) but not directly in local #1003

New Issue
Closed
opened 2026-04-12 10:42:54 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 10:42:54 -05:00
Owner
Copy Link

Originally created by @Huertas97 on GitHub (Dec 31, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1752

It is quite strange.
I have deployed the container of ollama and I can access to the bash shell and load models and chat with them. But when I install Ollama in the local system (the same that is running the docker container), when I try to chat with the same model (explored: tinyllama and mistral), it says:

Error: llama runner exited, you may not have enough available memory to run this model

Originally created by @Huertas97 on GitHub (Dec 31, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1752 It is quite strange. I have deployed the container of ollama and I can access to the bash shell and load models and chat with them. But when I install Ollama in the local system (the same that is running the docker container), when I try to chat with the same model (explored: tinyllama and mistral), it says: `Error: llama runner exited, you may not have enough available memory to run this model`
GiteaMirror commented 2026-04-12 10:42:55 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Dec 31, 2023):

Hi @Huertas97 what is your OS and how much memory you have? Try restart your computer and run Ollama directly in the system to test if it works. The memory allocated for docker could be still used and not available. Do you use the 0.1.17 version of Ollama?

<!-- gh-comment-id:1873023955 --> @igorschlum commented on GitHub (Dec 31, 2023): Hi @Huertas97 what is your OS and how much memory you have? Try restart your computer and run Ollama directly in the system to test if it works. The memory allocated for docker could be still used and not available. Do you use the 0.1.17 version of Ollama?
GiteaMirror commented 2026-04-12 10:42:55 -05:00
Author
Owner
Copy Link

@Huertas97 commented on GitHub (Jan 1, 2024):

Hi @igorschlum thank you for you quick response,

TL;DR:
Shutting down and starting the machine after installing Ollama from the Instalation Doc worked for me. Restarting was not enough.

More details if someone is facing similar problems:

My OS is Linux Lite based on Ubuntu 22.04.03 LTS. These are the details:

> cat /etc/os-release                                                    (base) 
PRETTY_NAME="Linux Lite 6.6"
NAME="Ubuntu"
VERSION_ID="22.04"
VERSION="22.04.3 LTS (Jammy Jellyfish)"
VERSION_CODENAME=jammy
ID=ubuntu
ID_LIKE=debian
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
UBUNTU_CODENAME=jammy

This OS is running in a machine with 16GB RAM DDR4.
I have installed the 0.1.17 Ollama version.

Wrapping up,
As proposed by @igorschlum restarting the machine (shutting it down completely) after installing Ollama solves it.

So I close the Issue thread

<!-- gh-comment-id:1873293856 --> @Huertas97 commented on GitHub (Jan 1, 2024): Hi @igorschlum thank you for you quick response, **TL;DR:** Shutting down and starting the machine after installing Ollama from the [Instalation Doc](https://ollama.ai/download) worked for me. Restarting was not enough. **More details if someone is facing similar problems:** My OS is Linux Lite based on Ubuntu 22.04.03 LTS. These are the details: ```shell > cat /etc/os-release (base) PRETTY_NAME="Linux Lite 6.6" NAME="Ubuntu" VERSION_ID="22.04" VERSION="22.04.3 LTS (Jammy Jellyfish)" VERSION_CODENAME=jammy ID=ubuntu ID_LIKE=debian HOME_URL="https://www.ubuntu.com/" SUPPORT_URL="https://help.ubuntu.com/" BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/" PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy" UBUNTU_CODENAME=jammy ``` This OS is running in a machine with 16GB RAM DDR4. I have installed the 0.1.17 Ollama version. Wrapping up, As proposed by @igorschlum restarting the machine (shutting it down completely) after installing Ollama solves it. So I close the Issue thread
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#1003
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?