[GH-ISSUE #3495] Supporting AQML #48663

Open
opened 2026-04-28 09:03:46 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @vaiju1981 on GitHub (Apr 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3495

What are you trying to do?

Support AQML quantized model in ollama. These models have very high quantization, but at the same time they are pretty comparable to original models.

How should we solve this?

By adding support https://github.com/Vahe1994/AQLM ( mostly via llama.cpp

What is the impact of not solving this?

This would enable very large llm to be loaded on smaller ( cpu bound machines )

Anything else?

No response

Originally created by @vaiju1981 on GitHub (Apr 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3495 ### What are you trying to do? Support AQML quantized model in ollama. These models have very high quantization, but at the same time they are pretty comparable to original models. ### How should we solve this? By adding support https://github.com/Vahe1994/AQLM ( mostly via llama.cpp ### What is the impact of not solving this? This would enable very large llm to be loaded on smaller ( cpu bound machines ) ### Anything else? _No response_
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#48663