[GH-ISSUE #9718] Ollama 0.6.0 like doubles all the memory sizes of models #68408

Closed
opened 2026-05-04 13:51:19 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @DavidePrati99 on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9718

What is the issue?

Phi4 (14b and 9.1gb, q4_K_M) had 13gb in previous versions, now is 30gb and does not fit anymore in my GPU.
The same thing happens for every model

Relevant log output


OS

No response

GPU

Nvidia

CPU

No response

Ollama version

0.6.0

Originally created by @DavidePrati99 on GitHub (Mar 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9718 ### What is the issue? Phi4 (14b and 9.1gb, q4_K_M) had 13gb in previous versions, now is 30gb and does not fit anymore in my GPU. The same thing happens for every model ### Relevant log output ```shell ``` ### OS _No response_ ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-05-04 13:51:19 -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#68408