github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 21:51:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1654] It takes forever to run ollama (llama2 or mistral) in wsl #926

New Issue
Closed
opened 2026-04-12 10:37:20 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 10:37:20 -05:00
Owner
Copy Link

Originally created by @allmin on GitHub (Dec 21, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1654

Hi I just installed ollama in wsl using curl. I tried ollama run llama2 and ollama run mistral.
It doesn't enter into the prompt. A tiny rotating snake like objects appears in the terminal and it has been several hours like this. Nothing much happened. please help me fix it.

My system:
Intel i7
RTXA2000 Laptop GPU : 4GB vRAM (0 GB used)

Originally created by @allmin on GitHub (Dec 21, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1654 Hi I just installed ollama in wsl using curl. I tried **ollama run llama2** and **ollama run mistral**. It doesn't enter into the prompt. A tiny rotating snake like objects appears in the terminal and it has been several hours like this. Nothing much happened. please help me fix it. My system: Intel i7 RTXA2000 Laptop GPU : 4GB vRAM (0 GB used)
GiteaMirror commented 2026-04-12 10:37:22 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Dec 21, 2023):

Hi @allmin
I think that you don't have enough memory. 4GB is nice, but not for IA. Try phi model. It's only a 1.6GB Gigabit file size, but can take more in GPU.
ollama run phi

<!-- gh-comment-id:1866982942 --> @igorschlum commented on GitHub (Dec 21, 2023): Hi @allmin I think that you don't have enough memory. 4GB is nice, but not for IA. Try phi model. It's only a 1.6GB Gigabit file size, but can take more in GPU. ollama run phi
GiteaMirror commented 2026-04-12 10:37:23 -05:00
Author
Owner
Copy Link

@allmin commented on GitHub (Dec 22, 2023):

Thank you! phi works!, I was indeed looking for smaller models but the
model library page: library (ollama.ai) https://ollama.ai/library was
lacking the information on memory requirements.

On Thu, Dec 21, 2023, 11:00 PM Igor Schlumberger @.***>
wrote:

Hi @allmin https://github.com/allmin
I think that you don't have enough memory. 4GB is nice, but not for IA.
Try phi model. It's only a 1.6GB Gigabit file size, but can take more in
GPU.
ollama run phi

—
Reply to this email directly, view it on GitHub
https://github.com/jmorganca/ollama/issues/1654#issuecomment-1866982942,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/ACNQU4PUQTMGRZC7CAJLGEDYKSWPHAVCNFSM6AAAAABA6K6FKKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNRWHE4DEOJUGI
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:1867646847 --> @allmin commented on GitHub (Dec 22, 2023): Thank you! phi works!, I was indeed looking for smaller models but the model library page: library (ollama.ai) <https://ollama.ai/library> was lacking the information on memory requirements. On Thu, Dec 21, 2023, 11:00 PM Igor Schlumberger ***@***.***> wrote: > Hi @allmin <https://github.com/allmin> > I think that you don't have enough memory. 4GB is nice, but not for IA. > Try phi model. It's only a 1.6GB Gigabit file size, but can take more in > GPU. > ollama run phi > > — > Reply to this email directly, view it on GitHub > <https://github.com/jmorganca/ollama/issues/1654#issuecomment-1866982942>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/ACNQU4PUQTMGRZC7CAJLGEDYKSWPHAVCNFSM6AAAAABA6K6FKKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNRWHE4DEOJUGI> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
GiteaMirror commented 2026-04-12 10:37:23 -05:00
Author
Owner
Copy Link

@allmin commented on GitHub (Dec 22, 2023):

BTW, It'd be helpful to also share here that I tried running llama2 through docker and it works perfectly on my 4GB GPU (Nvidia RTXA2000)!

<!-- gh-comment-id:1867654688 --> @allmin commented on GitHub (Dec 22, 2023): BTW, It'd be helpful to also share here that I tried running llama2 through docker and it works perfectly on my 4GB GPU (Nvidia RTXA2000)!
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
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#926
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?