github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3734] ollama create doesn't clean-up after 'creating model layer' failed #48811

New Issue
Closed
opened 2026-04-28 09:22:51 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 09:22:51 -05:00
Owner
Copy Link

Originally created by @PlanetMacro on GitHub (Apr 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3734

What is the issue?

If I try to create a model from local gguf files and the process exits with 'Error: invalid file magic' while performing 'creating model layer', the function does not clean up partial blobs that have been created. For larger models, this might build up substantial garbage data, that currently must be removed manually.

==================

Before the failed attempt to create a model:

user@debian-ai:~$ sudo du -ah / | awk '$1 ~ /G$/ && $1+0 > 10 {print}'
25G /usr/share/ollama/.ollama/models/blobs/sha256-e9e56e8bb5f0fcd4860675e6837a8f6a94e659f5fa7dce6a1076279336320f2b
94G /usr/share/ollama/.ollama/models/blobs/sha256-82440a94b304aa728bd12facfdc0eabe9ffcb3a64840be832401753f0bd8b0c0
47G /usr/share/ollama/.ollama/models/blobs/sha256-3a3c74c0bf306844ef6d255fbc4369769fd4a4c274f1fe9b6c55cf623cf56aed
[...]

Attempt to create the model:

user@debian-ai:~/Wizard-8x22B-Q5_K_M$ ollama create Wizard -f Modelfile
transferring model data
creating model layer
Error: invalid file magic

After the attempt:

user@debian-ai:~$ sudo du -ah / | awk '$1 ~ /G$/ && $1+0 > 10 {print}'
25G /usr/share/ollama/.ollama/models/blobs/sha256-e9e56e8bb5f0fcd4860675e6837a8f6a94e659f5fa7dce6a1076279336320f2b
22G /usr/share/ollama/.ollama/models/blobs/sha256-3939015911-partial
94G /usr/share/ollama/.ollama/models/blobs/sha256-82440a94b304aa728bd12facfdc0eabe9ffcb3a64840be832401753f0bd8b0c0
47G /usr/share/ollama/.ollama/models/blobs/sha256-3a3c74c0bf306844ef6d255fbc4369769fd4a4c274f1fe9b6c55cf623cf56aed
20G /usr/share/ollama/.ollama/models/blobs/sha256-24459609-partial
[...]

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.1.32

Originally created by @PlanetMacro on GitHub (Apr 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3734 ### What is the issue? If I try to create a model from local gguf files and the process exits with 'Error: invalid file magic' while performing 'creating model layer', the function does not clean up partial blobs that have been created. For larger models, this might build up substantial garbage data, that currently must be removed manually. ================== Before the failed attempt to create a model: user@debian-ai:~$ sudo du -ah / | awk '$1 ~ /G$/ && $1+0 > 10 {print}' 25G /usr/share/ollama/.ollama/models/blobs/sha256-e9e56e8bb5f0fcd4860675e6837a8f6a94e659f5fa7dce6a1076279336320f2b 94G /usr/share/ollama/.ollama/models/blobs/sha256-82440a94b304aa728bd12facfdc0eabe9ffcb3a64840be832401753f0bd8b0c0 47G /usr/share/ollama/.ollama/models/blobs/sha256-3a3c74c0bf306844ef6d255fbc4369769fd4a4c274f1fe9b6c55cf623cf56aed [...] Attempt to create the model: user@debian-ai:~/Wizard-8x22B-Q5_K_M$ ollama create Wizard -f Modelfile transferring model data creating model layer Error: invalid file magic After the attempt: user@debian-ai:~$ sudo du -ah / | awk '$1 ~ /G$/ && $1+0 > 10 {print}' 25G /usr/share/ollama/.ollama/models/blobs/sha256-e9e56e8bb5f0fcd4860675e6837a8f6a94e659f5fa7dce6a1076279336320f2b 22G /usr/share/ollama/.ollama/models/blobs/sha256-3939015911-partial 94G /usr/share/ollama/.ollama/models/blobs/sha256-82440a94b304aa728bd12facfdc0eabe9ffcb3a64840be832401753f0bd8b0c0 47G /usr/share/ollama/.ollama/models/blobs/sha256-3a3c74c0bf306844ef6d255fbc4369769fd4a4c274f1fe9b6c55cf623cf56aed 20G /usr/share/ollama/.ollama/models/blobs/sha256-24459609-partial [...] ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-28 09:22:51 -05:00
GiteaMirror commented 2026-04-28 09:23:17 -05:00
Author
Owner
Copy Link

@joshyan1 commented on GitHub (Jun 25, 2024):

Hey @PlanetMacro, are you still receiving this issue? If so, could you link the gguf file that you are using for import?

<!-- gh-comment-id:2190199301 --> @joshyan1 commented on GitHub (Jun 25, 2024): Hey @PlanetMacro, are you still receiving this issue? If so, could you link the gguf file that you are using for import?
GiteaMirror commented 2026-04-28 09:23:19 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 1, 2024):

Hi there, it seems this may have been an error fixed in newer versions of Ollama. Will close this for now but let us know if you're still seeing it @PlanetMacro

<!-- gh-comment-id:2200668984 --> @jmorganca commented on GitHub (Jul 1, 2024): Hi there, it seems this may have been an error fixed in newer versions of Ollama. Will close this for now but let us know if you're still seeing it @PlanetMacro
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#48811
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?