github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6263] Pull Command Parsing Not Working #3921

New Issue
Closed
opened 2026-04-12 14:47:32 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-12 14:47:32 -05:00
Owner
Copy Link

Originally created by @chadwickhar08 on GitHub (Aug 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6263

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When running ollama on Windows, attempt to run 'ollama pull llama3.1' results in 'ollama pull llama3.1
pulling manifest
Error: Incorrect function.'

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

ollama --version ollama version is 0.3.4

Originally created by @chadwickhar08 on GitHub (Aug 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6263 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When running ollama on Windows, attempt to run 'ollama pull llama3.1' results in 'ollama pull llama3.1 pulling manifest Error: Incorrect function.' ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version ollama --version ollama version is 0.3.4
GiteaMirror added the bugwindows labels 2026-04-12 14:47:32 -05:00
GiteaMirror commented 2026-04-12 14:47:35 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 8, 2024):

@chadwickhar08 is Ollama pulling other models like phi3:mini on your computer?

<!-- gh-comment-id:2276755907 --> @igorschlum commented on GitHub (Aug 8, 2024): @chadwickhar08 is Ollama pulling other models like phi3:mini on your computer?
GiteaMirror commented 2026-04-12 14:47:35 -05:00
Author
Owner
Copy Link

@chadwickhar08 commented on GitHub (Aug 8, 2024):

No, here is the output: 'ollama pull phi3:mini
pulling manifest
Error: Incorrect function.'

But a previously pulled mistral and several others work: 'ollama pull mistral
pulling manifest
pulling ff82381e2bea... 100% ▕████████████████▏ 4.1 GB
pulling 43070e2d4e53... 100% ▕████████████████▏ 11 KB
pulling 491dfa501e59... 100% ▕████████████████▏ 801 B
pulling ed11eda7790d... 100% ▕████████████████▏ 30 B
pulling 42347cd80dc8... 100% ▕████████████████▏ 485 B
verifying sha256 digest
writing manifest
removing any unused layers
success
'
'ollama pull gemma2
pulling manifest
pulling ff1d1fc78170... 100% ▕████████████████▏ 5.4 GB
pulling 109037bec39c... 100% ▕████████████████▏ 136 B
pulling 097a36493f71... 100% ▕████████████████▏ 8.4 KB
pulling 2490e7468436... 100% ▕████████████████▏ 65 B
pulling 10aa81da732e... 100% ▕████████████████▏ 487 B
verifying sha256 digest
writing manifest
removing any unused layers
success
'
'ollama pull deepseek-coder-v2
pulling manifest
pulling 5ff0abeeac1d... 100% ▕████████████████▏ 8.9 GB
pulling b321cd7de6c7... 100% ▕████████████████▏ 111 B
pulling 4bb71764481f... 100% ▕████████████████▏ 13 KB
pulling 1c8f573e830c... 100% ▕████████████████▏ 1.1 KB
pulling 19f2fb9e8bc6... 100% ▕████████████████▏ 32 B
pulling 34488e453cfe... 100% ▕████████████████▏ 568 B
verifying sha256 digest
writing manifest
removing any unused layers
success'

Additionally attempting to pull the llama3.1:405b model crashes ollama and my external filesystem on Windows. But that could be a separate bug.

<!-- gh-comment-id:2276774676 --> @chadwickhar08 commented on GitHub (Aug 8, 2024): No, here is the output: 'ollama pull phi3:mini pulling manifest Error: Incorrect function.' But a previously pulled mistral and several others work: 'ollama pull mistral pulling manifest pulling ff82381e2bea... 100% ▕████████████████▏ 4.1 GB pulling 43070e2d4e53... 100% ▕████████████████▏ 11 KB pulling 491dfa501e59... 100% ▕████████████████▏ 801 B pulling ed11eda7790d... 100% ▕████████████████▏ 30 B pulling 42347cd80dc8... 100% ▕████████████████▏ 485 B verifying sha256 digest writing manifest removing any unused layers success ' 'ollama pull gemma2 pulling manifest pulling ff1d1fc78170... 100% ▕████████████████▏ 5.4 GB pulling 109037bec39c... 100% ▕████████████████▏ 136 B pulling 097a36493f71... 100% ▕████████████████▏ 8.4 KB pulling 2490e7468436... 100% ▕████████████████▏ 65 B pulling 10aa81da732e... 100% ▕████████████████▏ 487 B verifying sha256 digest writing manifest removing any unused layers success ' 'ollama pull deepseek-coder-v2 pulling manifest pulling 5ff0abeeac1d... 100% ▕████████████████▏ 8.9 GB pulling b321cd7de6c7... 100% ▕████████████████▏ 111 B pulling 4bb71764481f... 100% ▕████████████████▏ 13 KB pulling 1c8f573e830c... 100% ▕████████████████▏ 1.1 KB pulling 19f2fb9e8bc6... 100% ▕████████████████▏ 32 B pulling 34488e453cfe... 100% ▕████████████████▏ 568 B verifying sha256 digest writing manifest removing any unused layers success' Additionally attempting to pull the llama3.1:405b model crashes ollama and my external filesystem on Windows. But that could be a separate bug.
GiteaMirror commented 2026-04-12 14:47:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Aug 9, 2024):

What version of Windows are you running? Is there anything special about the filesystem where you're storing models? Did 0.3.3 (or earlier) pull correctly?

We recently fixed a bug relating to how we handle sparse files, so perhaps that has an unintended side effect.

<!-- gh-comment-id:2278550143 --> @dhiltgen commented on GitHub (Aug 9, 2024): What version of Windows are you running? Is there anything special about the filesystem where you're storing models? Did 0.3.3 (or earlier) pull correctly? We recently fixed a bug relating to how we handle sparse files, so perhaps that has an unintended side effect.
GiteaMirror commented 2026-04-12 14:47:37 -05:00
Author
Owner
Copy Link

@chadwickhar08 commented on GitHub (Aug 9, 2024):

Hello,

I am running Windows 11. Nothing special about the external file system
other than I believe it is exFAT. The previous versions of Ollama worked
flawlessly, but not entirely sure if the llama3.1:405b still would have
pulled correctly since it is a newer model which coincides with the newer
Ollama release. I have been able to pull phi3 in the past but now with
trying to pull the model that I don't have, phi3:mini the error as noted
appears when in fact I had never encountered that issue before.

Thanks
-Chad H.

On Fri, Aug 9, 2024 at 2:52 PM Daniel Hiltgen @.***>
wrote:

What version of Windows are you running? Is there anything special about
the filesystem where you're storing models? Did 0.3.3 (or earlier) pull
correctly?

We recently fixed a bug relating to how we handle sparse files, so perhaps
that has an unintended side effect.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/6263#issuecomment-2278550143,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AFRJZYNYSJBRZBFHSSS7KQDZQUFVTAVCNFSM6AAAAABMHJA4U2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENZYGU2TAMJUGM
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:2278558247 --> @chadwickhar08 commented on GitHub (Aug 9, 2024): Hello, I am running Windows 11. Nothing special about the external file system other than I believe it is exFAT. The previous versions of Ollama worked flawlessly, but not entirely sure if the llama3.1:405b still would have pulled correctly since it is a newer model which coincides with the newer Ollama release. I have been able to pull phi3 in the past but now with trying to pull the model that I don't have, phi3:mini the error as noted appears when in fact I had never encountered that issue before. Thanks -Chad H. On Fri, Aug 9, 2024 at 2:52 PM Daniel Hiltgen ***@***.***> wrote: > What version of Windows are you running? Is there anything special about > the filesystem where you're storing models? Did 0.3.3 (or earlier) pull > correctly? > > We recently fixed a bug relating to how we handle sparse files, so perhaps > that has an unintended side effect. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/6263#issuecomment-2278550143>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AFRJZYNYSJBRZBFHSSS7KQDZQUFVTAVCNFSM6AAAAABMHJA4U2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENZYGU2TAMJUGM> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
GiteaMirror commented 2026-04-12 14:47:38 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Aug 9, 2024):

@chadwickhar08 thanks for that info. Yes, exFat does not support sparse files, so that explains the regression. We'll get this fixed in the next patch release. Sorry about that.

https://learn.microsoft.com/en-us/windows/win32/fileio/filesystem-functionality-comparison#functionality

<!-- gh-comment-id:2278564452 --> @dhiltgen commented on GitHub (Aug 9, 2024): @chadwickhar08 thanks for that info. Yes, exFat does not support sparse files, so that explains the regression. We'll get this fixed in the next patch release. Sorry about that. https://learn.microsoft.com/en-us/windows/win32/fileio/filesystem-functionality-comparison#functionality
GiteaMirror commented 2026-04-12 14:47:38 -05:00
Author
Owner
Copy Link

@chadwickhar08 commented on GitHub (Aug 9, 2024):

No worries, thanks!

-C

<!-- gh-comment-id:2278593097 --> @chadwickhar08 commented on GitHub (Aug 9, 2024): No worries, thanks! -C
GiteaMirror commented 2026-04-12 14:47:39 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 9, 2024):

@chadwickhar08 how much ram or vram have you on your PC?
New version of llama3.1 is being uploaded today.

<!-- gh-comment-id:2278782716 --> @igorschlum commented on GitHub (Aug 9, 2024): @chadwickhar08 how much ram or vram have you on your PC? New version of llama3.1 is being uploaded today.
GiteaMirror commented 2026-04-12 14:47:39 -05:00
Author
Owner
Copy Link

@chadwickhar08 commented on GitHub (Aug 9, 2024):

It is a RTX 3060(12GB) and 16 GB of ram. I have absolutely no intention of running the 405b model as I do not possess the hardware capabilities but rather am attempting to pull it as a means of storage.

<!-- gh-comment-id:2278784986 --> @chadwickhar08 commented on GitHub (Aug 9, 2024): It is a RTX 3060(12GB) and 16 GB of ram. I have absolutely no intention of running the 405b model as I do not possess the hardware capabilities but rather am attempting to pull it as a means of storage.
GiteaMirror commented 2026-04-12 14:47:40 -05:00
Author
Owner
Copy Link

@chadwickhar08 commented on GitHub (Aug 10, 2024):

That was quick! Very cool! Thanks Igor and everyone involved, super
impressive.

Take care,
-C

On Fri, Aug 9, 2024 at 5:32 PM Igor Schlumberger @.***>
wrote:

@chadwickhar08 https://github.com/chadwickhar08 how much ram or vram
have you on your PC?
New version of llama3.1 is being uploaded today.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/6263#issuecomment-2278782716,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AFRJZYNHK7YQ7PXM6OTVD53ZQUYPNAVCNFSM6AAAAABMHJA4U2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENZYG44DENZRGY
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:2278902352 --> @chadwickhar08 commented on GitHub (Aug 10, 2024): That was quick! Very cool! Thanks Igor and everyone involved, super impressive. Take care, -C On Fri, Aug 9, 2024 at 5:32 PM Igor Schlumberger ***@***.***> wrote: > @chadwickhar08 <https://github.com/chadwickhar08> how much ram or vram > have you on your PC? > New version of llama3.1 is being uploaded today. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/6263#issuecomment-2278782716>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AFRJZYNHK7YQ7PXM6OTVD53ZQUYPNAVCNFSM6AAAAABMHJA4U2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENZYG44DENZRGY> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
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#3921
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?