github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15149] qwen3.5 nvfp4 models say "this model requires macOS" #87388

New Issue
Closed
opened 2026-05-10 05:27:37 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-10 05:27:37 -05:00
Owner
Copy Link

Originally created by @duffyjp on GitHub (Mar 30, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15149

What is the issue?

$ ollama pull qwen3.5:9b-nvfp4
pulling manifest 
Error: pull model manifest: 412: this model requires macOS

$ ollama pull qwen3.5:35b-a3b-nvfp4
pulling manifest 
Error: pull model manifest: 412: this model requires macOS

I have a 5060 TI 16gb.

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.19.0

Originally created by @duffyjp on GitHub (Mar 30, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15149 ### What is the issue? ```bash $ ollama pull qwen3.5:9b-nvfp4 pulling manifest Error: pull model manifest: 412: this model requires macOS ``` ```bash $ ollama pull qwen3.5:35b-a3b-nvfp4 pulling manifest Error: pull model manifest: 412: this model requires macOS ``` I have a 5060 TI 16gb. ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.19.0
GiteaMirror added the bug label 2026-05-10 05:27:37 -05:00
GiteaMirror commented 2026-05-10 05:27:39 -05:00
Author
Owner
Copy Link

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

qwen3.5:9b-nvfp4 is an MLX model and requires the MLX backend to run, which is currently only supported on macOS.

<!-- gh-comment-id:4157778247 --> @rick-github commented on GitHub (Mar 30, 2026): qwen3.5:9b-nvfp4 is an MLX model and requires the MLX backend to run, which is currently only supported on macOS.
GiteaMirror commented 2026-05-10 05:27:41 -05:00
Author
Owner
Copy Link

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

Oh. Well that's a confusing name then, but okay.

<!-- gh-comment-id:4157853586 --> @duffyjp commented on GitHub (Mar 30, 2026): Oh. Well that's a confusing name then, but okay.
GiteaMirror commented 2026-05-10 05:27:43 -05:00
Author
Owner
Copy Link

@swoldemichael commented on GitHub (Apr 8, 2026):

Unless this nvfp4 refers to something different from the fp4 precision support on the nvidia blackwell gpus, this is a misnomer. nvfp4 is a hardware-native provision. This indicates to me, Apple engineers pushed their software implementation of fp4 on their hardware and called it nvfp4. You should at least put a readme not to confuse people.

<!-- gh-comment-id:4203947214 --> @swoldemichael commented on GitHub (Apr 8, 2026): Unless this nvfp4 refers to something different from the fp4 precision support on the nvidia blackwell gpus, this is a misnomer. nvfp4 is a hardware-native provision. This indicates to me, Apple engineers pushed their software implementation of fp4 on their hardware and called it nvfp4. You should at least put a readme not to confuse people.
GiteaMirror commented 2026-05-10 05:27:43 -05:00
Author
Owner
Copy Link

@JoeNunes commented on GitHub (May 7, 2026):

Why is this issue marked as closed? Do we need to download different modules before we find out what if they are compatible. This kind of segmentation of the open models on Ollama repos will damage trust. I have only downloaded newer models on LM Studio and was waiting for a proper update on here.

<!-- gh-comment-id:4394343863 --> @JoeNunes commented on GitHub (May 7, 2026): Why is this issue marked as closed? Do we need to download different modules before we find out what if they are compatible. This kind of segmentation of the open models on Ollama repos will damage trust. I have only downloaded newer models on LM Studio and was waiting for a proper update on here.
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#87388
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?