github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7425] Model loaded to RAM and not VRAM #30482

New Issue
Closed
opened 2026-04-22 10:08:05 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 10:08:05 -05:00
Owner
Copy Link

Originally created by @johanesalxd on GitHub (Oct 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7425

What is the issue?

image
server.log
lmstudio-issues
complete-specs

Model loaded to the RAM and not VRAM (7900 XTX), hence the performance is slow. I'm using Adrenalin 24.10.1 and having the same issue on other app as well (LM Studio) but I'm able to downgrade it's runtime so its running properly again.

image

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.3.14

Originally created by @johanesalxd on GitHub (Oct 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7425 ### What is the issue? ![image](https://github.com/user-attachments/assets/0b0cad75-7e33-4b6b-8f76-8dc5f9f95b7c) [server.log](https://github.com/user-attachments/files/17576314/server.log) [lmstudio-issues](https://discord.com/channels/1110598183144399058/1294935199892639834) [complete-specs](https://pcpartpicker.com/b/yDZZxr) Model loaded to the RAM and not VRAM (7900 XTX), hence the performance is slow. I'm using Adrenalin 24.10.1 and having the same issue on other app as well (LM Studio) but I'm able to _downgrade it's runtime_ so its running properly again. ![image](https://github.com/user-attachments/assets/0d8985f2-0535-4f4c-82da-0d0b7a961756) ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.3.14
GiteaMirror added the amdbugwindows labels 2026-04-22 10:08:05 -05:00
GiteaMirror commented 2026-04-22 10:08:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 30, 2024):

Known regression in the recent AMD drivers which should be fixed in 24.11.1

We're tracking this in #7107

<!-- gh-comment-id:2447802999 --> @dhiltgen commented on GitHub (Oct 30, 2024): Known regression in the recent AMD drivers which should be fixed in 24.11.1 We're tracking this in #7107
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 amd bug windows
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#30482
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?