[GH-ISSUE #8981] Is there some explain about quantization method #5829

Closed
opened 2026-04-12 17:10:26 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @estuday on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8981

hi,
i found ollama support quantization as follows:

Image

Is there some reference documentation that can explain the specific methods/meanings?
For example, i know that q4_0 and q4_1 is to quantize the model into int4, but what do 0 and 1 refer to respectively?

Originally created by @estuday on GitHub (Feb 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8981 hi, i found ollama support quantization as follows: ![Image](https://github.com/user-attachments/assets/81f40f5e-ce81-47ab-ab6d-91bbcbcadc28) Is there some reference documentation that can explain the specific methods/meanings? For example, i know that q4_0 and q4_1 is to quantize the model into int4, but what do 0 and 1 refer to respectively?
GiteaMirror added the question label 2026-04-12 17:10:26 -05:00
Author
Owner

@rick-github commented on GitHub (Feb 10, 2025):

https://andreshat.medium.com/llm-quantization-naming-explained-bedde33f7192

<!-- gh-comment-id:2647462664 --> @rick-github commented on GitHub (Feb 10, 2025): https://andreshat.medium.com/llm-quantization-naming-explained-bedde33f7192
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5829