github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10494] Entire model size being allocated to pagefile even with 100% GPU offload #68962

New Issue
Closed
opened 2026-05-04 16:28:27 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 16:28:27 -05:00
Owner
Copy Link

Originally created by @ethanblake4 on GitHub (Apr 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10494

What is the issue?

Using Ollama v0.6.6 with ROCm backend on Windows 11 (gfx1151).
When loading a model that is 100% GPU offloaded, Ollama 'commits' the entire size of the model to system memory regardless, which causes massive pagefiles to be created unnecessarily. It does not seem to be using this allocated space for anything, otherwise the memory would actually be used instead of just paged, so it just takes up extra SSD space for nothing.

Relevant log output

(base) PS C:\Users\home> ollama ps
NAME                     ID              SIZE      PROCESSOR    UNTIL
qwen2.5-coder:7b-base    bd8755145f1c    7.0 GB    100% GPU     24 minutes from now

OS

Windows 11

GPU

Radeon (TM) 8050S Graphics

CPU

AMD Ryzen AI Max PRO 390

Ollama version

0.6.6

Originally created by @ethanblake4 on GitHub (Apr 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10494 ### What is the issue? Using Ollama v0.6.6 with ROCm backend on Windows 11 (gfx1151). When loading a model that is 100% GPU offloaded, Ollama 'commits' the entire size of the model to system memory regardless, which causes massive pagefiles to be created unnecessarily. It does not seem to be using this allocated space for anything, otherwise the memory would actually be used instead of just paged, so it just takes up extra SSD space for nothing. ### Relevant log output ```shell (base) PS C:\Users\home> ollama ps NAME ID SIZE PROCESSOR UNTIL qwen2.5-coder:7b-base bd8755145f1c 7.0 GB 100% GPU 24 minutes from now ``` ### OS Windows 11 ### GPU Radeon (TM) 8050S Graphics ### CPU AMD Ryzen AI Max PRO 390 ### Ollama version 0.6.6
GiteaMirror added the bug label 2026-05-04 16:28:27 -05:00
GiteaMirror commented 2026-05-04 16:28:38 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 30, 2025):

Server logs may aid in debugging.

<!-- gh-comment-id:2841375119 --> @rick-github commented on GitHub (Apr 30, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#68962
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?