github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15141] ollama pull in Linux results in "this model requires macOS" #56206

New Issue
Closed
opened 2026-04-29 10:25:49 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-29 10:25:49 -05:00
Owner
Copy Link

Originally created by @donatas-xyz on GitHub (Mar 30, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15141

Originally assigned to: @BruceMacD on GitHub.

What is the issue?

Hi there,

Since upgrading to Ollama 0.19.0 I'm no longer able to download the latest Qwen3.5 27B model on Ubuntu 25.10, which has been released a day before and required an upgraded Ollama.

Relevant log output

linux:~$ ollama pull qwen3.5:27b-bf16
pulling manifest 
Error: pull model manifest: 412: this model requires macOS

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.19.0

Originally created by @donatas-xyz on GitHub (Mar 30, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15141 Originally assigned to: @BruceMacD on GitHub. ### What is the issue? Hi there, Since upgrading to Ollama 0.19.0 I'm no longer able to download the latest Qwen3.5 27B model on Ubuntu 25.10, which has been released a day before and required an upgraded Ollama. ### Relevant log output ```shell linux:~$ ollama pull qwen3.5:27b-bf16 pulling manifest Error: pull model manifest: 412: this model requires macOS ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.19.0
GiteaMirror added the bug label 2026-04-29 10:25:49 -05:00
GiteaMirror commented 2026-04-29 10:25:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 30, 2026):

qwen3.5:27b-bf16 is an MLX model, requiring the MLX backend to run, which is currently only supported on macOS.

<!-- gh-comment-id:4153505442 --> @rick-github commented on GitHub (Mar 30, 2026): qwen3.5:27b-bf16 is an MLX model, requiring the MLX backend to run, which is currently only supported on macOS.
GiteaMirror commented 2026-04-29 10:25:52 -05:00
Author
Owner
Copy Link

@donatas-xyz commented on GitHub (Mar 30, 2026):

Thank you, @rick-github. So where do I go from here then? 2-3 weeks ago I was able to download this model with ollama pull qwen3.5:27b-bf16, and now all of the sudden it's available for MacOS only?

<!-- gh-comment-id:4153572692 --> @donatas-xyz commented on GitHub (Mar 30, 2026): Thank you, @rick-github. So where do I go from here then? 2-3 weeks ago I was able to download this model with `ollama pull qwen3.5:27b-bf16`, and now all of the sudden it's available for MacOS only?
GiteaMirror commented 2026-04-29 10:25:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 30, 2026):

I'm guessing it was inadvertently overwritten when the MLX version of the model was uploaded. I've pushed the original GGUF version to frob/qwen3.5:27b-gguf-bf16.

<!-- gh-comment-id:4153718032 --> @rick-github commented on GitHub (Mar 30, 2026): I'm guessing it was inadvertently overwritten when the MLX version of the model was uploaded. I've pushed the original GGUF version to [frob/qwen3.5:27b-gguf-bf16](https://ollama.com/frob/qwen3.5:27b-gguf-bf16).
GiteaMirror commented 2026-04-29 10:25:55 -05:00
Author
Owner
Copy Link

@donatas-xyz commented on GitHub (Mar 30, 2026):

Thank you, @rick-github - this one is downloading. I'm a bit behind the times, when it comes to "custom" models and I always tend to stick with the "official" Ollama versions, so can I assume this qwen3.5:27b-gguf-bf16 model is the same as the previous non-MLX version?

<!-- gh-comment-id:4153801710 --> @donatas-xyz commented on GitHub (Mar 30, 2026): Thank you, @rick-github - this one is downloading. I'm a bit behind the times, when it comes to "custom" models and I always tend to stick with the "official" Ollama versions, so can I assume this `qwen3.5:27b-gguf-bf16` model is the same as the previous non-MLX version?
GiteaMirror commented 2026-04-29 10:25:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 30, 2026):

Yes, it's the same as the previous non-MLX version.

<!-- gh-comment-id:4153888635 --> @rick-github commented on GitHub (Mar 30, 2026): Yes, it's the same as the previous non-MLX version.
GiteaMirror commented 2026-04-29 10:25:56 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 30, 2026):

Sorry about this, mistakenly pushed while uploading safe tensor weights for MLX. The original gguf weights have been restored in the repo. Thanks for reporting this.

<!-- gh-comment-id:4157311190 --> @BruceMacD commented on GitHub (Mar 30, 2026): Sorry about this, mistakenly pushed while uploading safe tensor weights for MLX. The original gguf weights have been restored in the repo. Thanks for reporting this.
GiteaMirror commented 2026-04-29 10:25:56 -05:00
Author
Owner
Copy Link

@donatas-xyz commented on GitHub (Apr 8, 2026):

Hi, @BruceMacD. Thank you for your help with the issue.

I believe qwen3.5:27b-coding-bf16 is still meant for MLX though, so this one could be re-uploaded as well, that would be great.

Thank you!

<!-- gh-comment-id:4204787764 --> @donatas-xyz commented on GitHub (Apr 8, 2026): Hi, @BruceMacD. Thank you for your help with the issue. I believe `qwen3.5:27b-coding-bf16` is still meant for MLX though, so this one could be re-uploaded as well, that would be great. Thank you!
GiteaMirror commented 2026-04-29 10:25:57 -05:00
Author
Owner
Copy Link

@fieryWaters commented on GitHub (Apr 23, 2026):

This issue is happening again for qwen 3.6 27b.

jacob@MacBookAir ~ % ollama run qwen3.6:27b-coding-bf16
pulling manifest
Error: pull model manifest: 412: this model requires macOS
jacob@MacBookAir ~ % `

<!-- gh-comment-id:4307047752 --> @fieryWaters commented on GitHub (Apr 23, 2026): This issue is happening again for qwen 3.6 27b. `jacob@MacBookAir` ~ % ollama run qwen3.6:27b-coding-bf16 pulling manifest Error: pull model manifest: 412: this model requires macOS jacob@MacBookAir ~ % `
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#56206
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?