[GH-ISSUE #13722] qwen2.4-vl:7b memory uses increases 50% when using Ollama versions >0.13.3 #34756

Closed
opened 2026-04-22 18:34:59 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @mikey60 on GitHub (Jan 15, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13722

What is the issue?

After upgrading Ollama to any version >0.13.3 The VRAM usage of model qwen2.4-vl:7b increases 50%. I expected the memory usage to be the same.
My ollama ps results:
Any version > 0.13.3
NAME ID SIZE PROCESSOR CONTEXT UNTIL
qwen2.5vl:7b 5ced39dfa4ba 14 GB 100% GPU 16384 4 minutes from now

version 0.13.3
NAME ID SIZE PROCESSOR CONTEXT UNTIL
qwen2.5vl:7b 5ced39dfa4ba 9.4 GB 100% GPU 16384 4 minutes from

Relevant log output


OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.13.4

Originally created by @mikey60 on GitHub (Jan 15, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13722 ### What is the issue? After upgrading Ollama to any version >0.13.3 The VRAM usage of model qwen2.4-vl:7b increases 50%. I expected the memory usage to be the same. My ollama ps results: **Any version > 0.13.3** NAME ID SIZE PROCESSOR CONTEXT UNTIL qwen2.5vl:7b 5ced39dfa4ba 14 GB 100% GPU 16384 4 minutes from now **version 0.13.3** NAME ID SIZE PROCESSOR CONTEXT UNTIL qwen2.5vl:7b 5ced39dfa4ba 9.4 GB 100% GPU 16384 4 minutes from ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.13.4
GiteaMirror added the bug label 2026-04-22 18:34:59 -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#34756