github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2000] Issue with Ollama on Ubuntu 22.04 under VirtualBox 7 Windows 11 #1153

New Issue
Closed
opened 2026-04-12 10:55:00 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 10:55:00 -05:00
Owner
Copy Link

Originally created by @dekogroup on GitHub (Jan 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2000

Originally assigned to: @dhiltgen on GitHub.

On this platform, Ollama was installed successfully but got following error when running:

ollama run codellama:7b-instruct

Illegal instruction (core dumped)

Originally created by @dekogroup on GitHub (Jan 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2000 Originally assigned to: @dhiltgen on GitHub. On this platform, Ollama was installed successfully but got following error when running: ollama run codellama:7b-instruct Illegal instruction (core dumped)
GiteaMirror commented 2026-04-12 10:55:02 -05:00
Author
Owner
Copy Link

@Rushmore75 commented on GitHub (Jan 19, 2024):

Getting same result, on any command, I'm using Proxmox 8.1.3 tho

<!-- gh-comment-id:1899655135 --> @Rushmore75 commented on GitHub (Jan 19, 2024): Getting same result, on any command, I'm using Proxmox 8.1.3 tho
GiteaMirror commented 2026-04-12 10:55:02 -05:00
Author
Owner
Copy Link

@Rushmore75 commented on GitHub (Jan 19, 2024):

@dekogroup try building from source and bumping up the version of the mimetype depdendancy

<!-- gh-comment-id:1899822585 --> @Rushmore75 commented on GitHub (Jan 19, 2024): @dekogroup try building from source and bumping up the version of the mimetype depdendancy
GiteaMirror commented 2026-04-12 10:55:02 -05:00
Author
Owner
Copy Link

@dekogroup commented on GitHub (Jan 19, 2024):

Thank you @Rushmore75 . Will try.

<!-- gh-comment-id:1900161334 --> @dekogroup commented on GitHub (Jan 19, 2024): Thank you @Rushmore75 . Will try.
GiteaMirror commented 2026-04-12 10:55:03 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 26, 2024):

@dekogroup my suspicion is you have VirtualBox configured to mask CPU features like AVX and AVX2. In older builds, we'd crash with illegal instruction. We have recently added support for running on CPUs without these vector math extensions, but if you can update your VirtualBox configuration, I'd recommend that as it will result in better performance if we have to do any inference on the CPU.

<!-- gh-comment-id:1912715880 --> @dhiltgen commented on GitHub (Jan 26, 2024): @dekogroup my suspicion is you have VirtualBox configured to mask CPU features like AVX and AVX2. In older builds, we'd crash with illegal instruction. We have recently added support for running on CPUs without these vector math extensions, but if you can update your VirtualBox configuration, I'd recommend that as it will result in better performance if we have to do any inference on the CPU.
GiteaMirror commented 2026-04-12 10:55:03 -05:00
Author
Owner
Copy Link

@orlyandico commented on GitHub (Feb 3, 2024):

Not an exact answer, but Ollama works great on WSL2 with Ubuntu 22.04 on Windows 11. That's HyperV underneath. GPU works fine and there's no performance hit that I can measure.

<!-- gh-comment-id:1925088244 --> @orlyandico commented on GitHub (Feb 3, 2024): Not an exact answer, but Ollama works great on WSL2 with Ubuntu 22.04 on Windows 11. That's HyperV underneath. GPU works fine and there's no performance hit that I can measure.
GiteaMirror commented 2026-04-12 10:55:04 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Feb 19, 2024):

Recent builds will no longer crash, but will not execute on the GPU due to lacking AVX support. Potentially adding non-AVX support to the GPU builds is tracked via issue #2187

<!-- gh-comment-id:1953082116 --> @dhiltgen commented on GitHub (Feb 19, 2024): Recent builds will no longer crash, but will not execute on the GPU due to lacking AVX support. Potentially adding non-AVX support to the GPU builds is tracked via issue #2187
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#1153
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?