[GH-ISSUE #120] Are the models quantizated? #25802

Closed
opened 2026-04-22 01:37:26 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @chsasank on GitHub (Jul 19, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/120

Can you give more details on quantization level the models are running and if they can be changed?

Originally created by @chsasank on GitHub (Jul 19, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/120 Can you give more details on quantization level the models are running and if they can be changed?
Author
Owner

@mchiang0610 commented on GitHub (Jul 19, 2023):

Right now, we curate models using 4-bit quantization. We do want to support changing quantizations in the future -- whether this is submitted by users or we curate them are to be decided.

Hope this answers your question.

Feel free to join our Discord to chat more!

Discord

Thanks

<!-- gh-comment-id:1641515409 --> @mchiang0610 commented on GitHub (Jul 19, 2023): Right now, we curate models using 4-bit quantization. We do want to support changing quantizations in the future -- whether this is submitted by users or we curate them are to be decided. Hope this answers your question. Feel free to join our Discord to chat more! [Discord](https://discord.gg/MrfB5FbNWN) Thanks
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#25802