[GH-ISSUE #13466] Exceptional memory usage when using the qwen model on ollamas #70945

Closed
opened 2026-05-04 23:32:23 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @ynqjwsm on GitHub (Dec 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13466

What is the issue?

os:Darwin 24.6.0 Darwin Kernel Version 24.6.0: Wed Oct 15 21:12:15 PDT 2025; root:xnu-11417.140.69.703.14~1/RELEASE_ARM64_T6041 arm64
ollama version:ollama version is 0.13.3
model:qwen3-next:80b-a3b-instruct-q4_K_M(5bb9dcc938cc)
union memory usage:110GB(too large, model weight file is 50GB)
NAME ID SIZE PROCESSOR CONTEXT UNTIL
qwen3-next:80b-a3b-instruct-q4_K_M 5bb9dcc938cc 110 GB 9%/91% CPU/GPU 262144 14 seconds from now

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @ynqjwsm on GitHub (Dec 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13466 ### What is the issue? os:Darwin 24.6.0 Darwin Kernel Version 24.6.0: Wed Oct 15 21:12:15 PDT 2025; root:xnu-11417.140.69.703.14~1/RELEASE_ARM64_T6041 arm64 ollama version:ollama version is 0.13.3 model:qwen3-next:80b-a3b-instruct-q4_K_M(5bb9dcc938cc) union memory usage:110GB(too large, model weight file is 50GB) NAME ID SIZE PROCESSOR CONTEXT UNTIL qwen3-next:80b-a3b-instruct-q4_K_M 5bb9dcc938cc 110 GB 9%/91% CPU/GPU 262144 14 seconds from now ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 23:32:23 -05:00
Author
Owner

@rick-github commented on GitHub (Dec 14, 2025):

Reduce the size of the context.

<!-- gh-comment-id:3650255509 --> @rick-github commented on GitHub (Dec 14, 2025): Reduce the size of the context.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#70945