[GH-ISSUE #4637] windows gpu memory.available always be one value #64951

Closed
opened 2026-05-03 19:22:52 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @mofanke on GitHub (May 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4637

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

windows gpu memory.available always be one value , no matter how many model was loaded

OS

Windows

GPU

Nvidia

CPU

No response

Ollama version

0.1.38

Originally created by @mofanke on GitHub (May 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4637 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? windows gpu memory.available always be one value , no matter how many model was loaded ### OS Windows ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.1.38
GiteaMirror added the bugwindows labels 2026-05-03 19:22:52 -05:00
Author
Owner

@mofanke commented on GitHub (May 25, 2024):

1716620117668_568E211C-74B5-44a1-887B-B3DD1C1E6BBE

<!-- gh-comment-id:2131301738 --> @mofanke commented on GitHub (May 25, 2024): ![1716620117668_568E211C-74B5-44a1-887B-B3DD1C1E6BBE](https://github.com/ollama/ollama/assets/54242816/589cc9aa-d503-48a3-a3c5-774657dc5886)
Author
Owner

@mofanke commented on GitHub (May 25, 2024):

server.log
here is my server log

<!-- gh-comment-id:2131301839 --> @mofanke commented on GitHub (May 25, 2024): [server.log](https://github.com/ollama/ollama/files/15443974/server.log) here is my server log
Author
Owner

@dhiltgen commented on GitHub (May 31, 2024):

Tracked via #4599

<!-- gh-comment-id:2142900964 --> @dhiltgen commented on GitHub (May 31, 2024): Tracked via #4599
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#64951