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 #14532] Ollama 0.17.4 Eats GPU Memory #55940

New Issue
Closed
opened 2026-04-29 09:58:34 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 09:58:34 -05:00
Owner
Copy Link

Originally created by @intlex on GitHub (Mar 1, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14532

What is the issue?

Ollama's GPU memory usage has increased significantly after the latest update. Specifically, the Qwen3-vl:30b model is now consuming all available GPU memory, whereas before the update the memory usage was reasonable. I'm also seeing a noticeable increase in memory usage with Gemma3, roughly 1.5x higher than before the update.

Relevant log output

{"models":[{"name":"qwen3-vl:30b","model":"qwen3-vl:30b","size":52268062016,"digest":"eda0be1008774ea4e575187712b9a3b1201f3e66e7ecff899cc295db1cf00248","details":{"parent_model":"","format":"gguf","family":"qwen3vlmoe","families":["qwen3vlmoe"],"parameter_size":"31.1B","quantization_level":"Q4_K_M"},"expires_at":"2026-03-01T18:17:27.563275303+03:00","size_vram":50649865600,"context_length":262144}]}

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.17.4

Originally created by @intlex on GitHub (Mar 1, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14532 ### What is the issue? Ollama's GPU memory usage has increased significantly after the latest update. Specifically, the Qwen3-vl:30b model is now consuming all available GPU memory, whereas before the update the memory usage was reasonable. I'm also seeing a noticeable increase in memory usage with Gemma3, roughly 1.5x higher than before the update. ### Relevant log output ```shell {"models":[{"name":"qwen3-vl:30b","model":"qwen3-vl:30b","size":52268062016,"digest":"eda0be1008774ea4e575187712b9a3b1201f3e66e7ecff899cc295db1cf00248","details":{"parent_model":"","format":"gguf","family":"qwen3vlmoe","families":["qwen3vlmoe"],"parameter_size":"31.1B","quantization_level":"Q4_K_M"},"expires_at":"2026-03-01T18:17:27.563275303+03:00","size_vram":50649865600,"context_length":262144}]} ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.17.4
GiteaMirror added the bug label 2026-04-29 09:58:34 -05:00
GiteaMirror commented 2026-04-29 09:58:37 -05:00
Author
Owner
Copy Link

@intlex commented on GitHub (Mar 1, 2026):

found this https://github.com/ollama/ollama/issues/14116

<!-- gh-comment-id:3980346861 --> @intlex commented on GitHub (Mar 1, 2026): found this https://github.com/ollama/ollama/issues/14116
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#55940
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?