[GH-ISSUE #6808] qos, serving websites with the server, but when downloading a model... #30058

Open
opened 2026-04-22 09:29:43 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @remco-pc on GitHub (Sep 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6808

if a big model gets loaded, it loads at full speed, slowing down other services. can you make a throttle to only allow a certain amount of bandwidth consumed by downloading the model.

I try to have websites running on that server, and they become unresponsive due to the model download (tested it with llama3.1:70b)

Originally created by @remco-pc on GitHub (Sep 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6808 if a big model gets loaded, it loads at full speed, slowing down other services. can you make a throttle to only allow a certain amount of bandwidth consumed by downloading the model. I try to have websites running on that server, and they become unresponsive due to the model download (tested it with llama3.1:70b)
GiteaMirror added the feature request label 2026-04-22 09:29:43 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#30058