[GH-ISSUE #6070] Run Ollama on multiple GPU using ollama run #3792

Closed
opened 2026-04-12 14:37:33 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @atharvnagrikar on GitHub (Jul 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6070

Originally assigned to: @dhiltgen on GitHub.

Hi,
I have 2 gpus each having 40 gb of memory and i want to run llama3.1 70b using these GPUs, are there any features to run ollama on distributed way

Originally created by @atharvnagrikar on GitHub (Jul 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6070 Originally assigned to: @dhiltgen on GitHub. Hi, I have 2 gpus each having 40 gb of memory and i want to run llama3.1 70b using these GPUs, are there any features to run ollama on distributed way
GiteaMirror added the feature request label 2026-04-12 14:37:34 -05:00
Author
Owner

@rick-github commented on GitHub (Jul 30, 2024):

ollama will use multiple GPUs if available. If you tried it and it didn't work, adding server logs will aid in debugging.

<!-- gh-comment-id:2258529873 --> @rick-github commented on GitHub (Jul 30, 2024): ollama will use multiple GPUs if available. If you tried it and it didn't work, adding server logs will aid in debugging.
Author
Owner

@dhiltgen commented on GitHub (Jul 30, 2024):

@atharvnagrikar let us know if you have any problems loading the model and if so I'll reopen.

<!-- gh-comment-id:2258807734 --> @dhiltgen commented on GitHub (Jul 30, 2024): @atharvnagrikar let us know if you have any problems loading the model and if so I'll reopen.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3792