github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4469] Ollama memory consumption #49302

New Issue
Closed
opened 2026-04-28 11:10:00 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 11:10:00 -05:00
Owner
Copy Link

Originally created by @hugefrog on GitHub (May 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4469

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Why does Ollama consume so much memory? With a 3090 graphics card and 24GB of VRAM, after loading a yi-34b-4bit model of around 20GB in size, both the system memory and VRAM are consumed by approximately 20GB simultaneously.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.38

Originally created by @hugefrog on GitHub (May 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4469 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Why does Ollama consume so much memory? With a 3090 graphics card and 24GB of VRAM, after loading a yi-34b-4bit model of around 20GB in size, both the system memory and VRAM are consumed by approximately 20GB simultaneously. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.38
GiteaMirror added the bugwindows labels 2026-04-28 11:10:00 -05:00
GiteaMirror commented 2026-04-28 11:10:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 25, 2024):

I'm not able to reproduce this. On windows on a 4090, I can load yi:34b entirely into GPU:

>  ollama ps
NAME    ID              SIZE    PROCESSOR       UNTIL
yi:34b  ff94bc7c1b7a    20 GB   100% GPU        4 minutes from now

The ollama_llama_server process uses 929 MB of system memory, and ~20G of VRAM according to Task Manager.

Are you using a larger context size that is causing the model to partially load on CPU?

If you're still seeing large system memory consumption, please make sure to upgrade to the latest version, and share more details of your setup and I'll reopen the issue. (ollama ps output, screen shots from task manager, and server logs)

<!-- gh-comment-id:2251531637 --> @dhiltgen commented on GitHub (Jul 25, 2024): I'm not able to reproduce this. On windows on a 4090, I can load `yi:34b` entirely into GPU: ``` > ollama ps NAME ID SIZE PROCESSOR UNTIL yi:34b ff94bc7c1b7a 20 GB 100% GPU 4 minutes from now ``` The `ollama_llama_server` process uses 929 MB of system memory, and ~20G of VRAM according to Task Manager. Are you using a larger context size that is causing the model to partially load on CPU? If you're still seeing large system memory consumption, please make sure to upgrade to the latest version, and share more details of your setup and I'll reopen the issue. (`ollama ps` output, screen shots from task manager, and server logs)
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 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#49302
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?