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 #3139] low ram usage #63970

New Issue
Closed
opened 2026-05-03 15:36:01 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 15:36:01 -05:00
Owner
Copy Link

Originally created by @parzzd on GitHub (Mar 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3139

i have a problem with the ram usage for qwen_1_5_4b
i have 16gb ram, but the software only use 1.6gb
is there a way to dedicate more ram to ollama process?

Originally created by @parzzd on GitHub (Mar 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3139 i have a problem with the ram usage for qwen_1_5_4b i have 16gb ram, but the software only use 1.6gb is there a way to dedicate more ram to ollama process?
GiteaMirror added the question label 2026-05-03 15:36:01 -05:00
GiteaMirror commented 2026-05-03 15:36:06 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 14, 2024):

Hey @parzzd , you're actually using a 4b parameter 4bit quantized version of qwen. If you don't want to use as heavily quantized version of that model you can:

ollama run qwen:4b-chat-v1.5-fp16

That should take about 9GB of RAM using a non-quantized model. You can try using a higher parameter count (like 7b) and play around with what level of quantization that you want.

I'll go ahead and close the issue, but feel free to keep commenting.

<!-- gh-comment-id:1998284967 --> @pdevine commented on GitHub (Mar 14, 2024): Hey @parzzd , you're actually using a 4b parameter 4bit quantized version of qwen. If you don't want to use as heavily quantized version of that model you can: ``` ollama run qwen:4b-chat-v1.5-fp16 ``` That should take about 9GB of RAM using a non-quantized model. You can try using a higher parameter count (like 7b) and play around with what level of quantization that you want. I'll go ahead and close the issue, but feel free to keep commenting.
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 question
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#63970
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?