github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7566] Having trouble with vram using priority #51330

New Issue
Closed
opened 2026-04-28 19:30:19 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 19:30:19 -05:00
Owner
Copy Link

Originally created by @morika546 on GitHub (Nov 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7566

What is the issue?

My GPU is 6800xt with 16 GB VRAM,and my RAM is 64 GB.When I running the model,It always using so many shared VRAM while there is still a lot of free dedicated VRAM.For example, when I run a 13 b sized model,it needs 12GB VRAM,and only 4GB Runs by dedicated VRAM,the resist 8GB runs by shared VRAM,That makes even the processor is 100% GPU,the model still runs in a very very slow speed.
I have checked the serve.log,and doubt if this makes the problem:

time=2024-11-06T22:18:35.707+08:00 level=INFO source=sched.go:185 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency

I am new to ollama,and have been suffering from the bug for two weeks,I will appreciate it if anyone can help me.Here is the full serve.log:

2_server.log

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.4.0

Originally created by @morika546 on GitHub (Nov 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7566 ### What is the issue? My GPU is 6800xt with 16 GB VRAM,and my RAM is 64 GB.When I running the model,It always using so many shared VRAM while there is still a lot of free dedicated VRAM.For example, when I run a 13 b sized model,it needs 12GB VRAM,and only 4GB Runs by dedicated VRAM,the resist 8GB runs by shared VRAM,That makes even the processor is 100% GPU,the model still runs in a very very slow speed. I have checked the serve.log,and doubt if this makes the problem: time=2024-11-06T22:18:35.707+08:00 level=INFO source=sched.go:185 msg="one or more GPUs detected that are unable to accurately report free memory - disabling default concurrency I am new to ollama,and have been suffering from the bug for two weeks,I will appreciate it if anyone can help me.Here is the full serve.log: [2_server.log](https://github.com/user-attachments/files/17672177/2_server.log) ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.4.0
GiteaMirror added the bug label 2026-04-28 19:30:19 -05:00
GiteaMirror commented 2026-04-28 19:31:49 -05:00
Author
Owner
Copy Link

@morika546 commented on GitHub (Nov 8, 2024):

solved by reinstall Redon gpu driver 24.8.1

<!-- gh-comment-id:2464207995 --> @morika546 commented on GitHub (Nov 8, 2024): solved by reinstall Redon gpu driver 24.8.1
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#51330
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?