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 #1090] Suggestions for instruction clarifications for running in docker in Windows. #62577

New Issue
Closed
opened 2026-05-03 09:36:06 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 09:36:06 -05:00
Owner
Copy Link

Originally created by @pdavis68 on GitHub (Nov 11, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1090

Originally assigned to: @dhiltgen on GitHub.

I just got this installed in Windows using Docker.

The instructions were a bit unclear since the instructions for installing the Nvidia stuff is Linux based. I mistakenly thought I needed to run the container and install all the Nvidia stuff in the container. . It might help other people like me who aren't so clever to know that those are Linux-specific instructions for installing the Nvidia drivers and adding instructions for installing the Nvidia drivers under Windows.

For Windows, you can install the Nvidia drivers (though I'm not sure which ones I installed that worked for this, because I've had them installed for a while. I have the basic drivers and CUDA. I'm guessing it's using the CUDA drivers.) and then run it with the GPU as per the instructions, it worked like a charm.

Also, just want to say, really nice work. I've tried installing a few of these local LLMs and this was by far the easiest for me to install (despite the above issues) and it works really well. I couldn't be happier.

I've been working on a game that uses LLMs and the cost of running with OpenAI was going to be higher than I'd like, so I've been waiting for a local version I could use instead and you guys have delivered. I'm really excited about this.

Originally created by @pdavis68 on GitHub (Nov 11, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1090 Originally assigned to: @dhiltgen on GitHub. I just got this installed in Windows using Docker. The instructions were a bit unclear since the instructions for installing the Nvidia stuff is Linux based. I mistakenly thought I needed to run the container and install all the Nvidia stuff in the container. . It might help other people like me who aren't so clever to know that those are Linux-specific instructions for installing the Nvidia drivers and adding instructions for installing the Nvidia drivers under Windows. For Windows, you can install the Nvidia drivers (though I'm not sure which ones I installed that worked for this, because I've had them installed for a while. I have the basic drivers and CUDA. I'm guessing it's using the CUDA drivers.) and then run it with the GPU as per the instructions, it worked like a charm. Also, just want to say, really nice work. I've tried installing a few of these local LLMs and this was by far the easiest for me to install (despite the above issues) and it works really well. I couldn't be happier. I've been working on a game that uses LLMs and the cost of running with OpenAI was going to be higher than I'd like, so I've been waiting for a local version I could use instead and you guys have delivered. I'm really excited about this.
GiteaMirror added the documentation label 2026-05-03 09:36:06 -05:00
GiteaMirror commented 2026-05-03 09:36:08 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 12, 2024):

I'm inclined to close this one now that we have a native Windows version available that supports both Nvidia and AMD GPUs. For most users, that's going to be a far better option than WSL2. WSL2 still works and we'll continue to support it for folks who want to use it, but the simple flow is just run OllamaSetup.exe and as long as you've installed the Nvidia or AMD driver for your GPU, and have a supported GPU, it should just work.

<!-- gh-comment-id:1991961688 --> @dhiltgen commented on GitHub (Mar 12, 2024): I'm inclined to close this one now that we have a native Windows version available that supports both Nvidia and AMD GPUs. For most users, that's going to be a far better option than WSL2. WSL2 still works and we'll continue to support it for folks who want to use it, but the simple flow is just run `OllamaSetup.exe` and as long as you've installed the Nvidia or AMD driver for your GPU, and have a supported GPU, it should just work.
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 documentation
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#62577
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?