github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5484] Unnecessary use of GPUs when I run "ollama pull" #49941

New Issue
Closed
opened 2026-04-28 13:30:19 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 13:30:19 -05:00
Owner
Copy Link

Originally created by @eliranwong on GitHub (Jul 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5484

What is the issue?

When I run "ollama pull" to just download modules, e.g.

ollama pull deepseek-v2:16b

Both of my GPUs are fully 100% used, which is unnecessary for download task ONLY.

========================================== ROCm System Management Interface ==========================================
==================================================== Concise Info ====================================================
Device  Node  IDs              Temp    Power   Partitions          SCLK     MCLK   Fan     Perf  PwrCap  VRAM%  GPU%  
              (DID,     GUID)  (Edge)  (Avg)   (Mem, Compute, ID)                                                     
======================================================================================================================
0       2     0x744c,   45048  66.0°C  138.0W  N/A, N/A, 0         3138Mhz  96Mhz  22.75%  auto  327.0W  29%    100%  
1       1     0x744c,   12575  58.0°C  136.0W  N/A, N/A, 0         3052Mhz  96Mhz  14.9%   auto  327.0W  29%    100%  
======================================================================================================================
================================================ End of ROCm SMI Log =================================================

Remarks: I run ROCm 6.1.3 for my dual AMD RX 7900 XTX

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.1.47

Originally created by @eliranwong on GitHub (Jul 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5484 ### What is the issue? When I run "ollama pull" to just download modules, e.g. > ollama pull deepseek-v2:16b Both of my GPUs are fully 100% used, which is unnecessary for download task ONLY. ``` ========================================== ROCm System Management Interface ========================================== ==================================================== Concise Info ==================================================== Device Node IDs Temp Power Partitions SCLK MCLK Fan Perf PwrCap VRAM% GPU% (DID, GUID) (Edge) (Avg) (Mem, Compute, ID) ====================================================================================================================== 0 2 0x744c, 45048 66.0°C 138.0W N/A, N/A, 0 3138Mhz 96Mhz 22.75% auto 327.0W 29% 100% 1 1 0x744c, 12575 58.0°C 136.0W N/A, N/A, 0 3052Mhz 96Mhz 14.9% auto 327.0W 29% 100% ====================================================================================================================== ================================================ End of ROCm SMI Log ================================================= ``` Remarks: I run ROCm 6.1.3 for my dual AMD RX 7900 XTX ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.1.47
GiteaMirror added the bug label 2026-04-28 13:30:19 -05:00
GiteaMirror commented 2026-04-28 13:30:23 -05:00
Author
Owner
Copy Link

@eliranwong commented on GitHub (Jul 4, 2024):

sorry, I reboot and run ollama pull qwen2:72b and it seems fine. I guessed I had some other tasks running on the background that I was not aware of. I am closing this issue now.

<!-- gh-comment-id:2208885395 --> @eliranwong commented on GitHub (Jul 4, 2024): sorry, I reboot and run `ollama pull qwen2:72b` and it seems fine. I guessed I had some other tasks running on the background that I was not aware of. I am closing this issue now.
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#49941
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?