github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15503] is your article about MLX support fake? #35669

New Issue
Closed
opened 2026-04-22 20:20:38 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 20:20:38 -05:00
Owner
Copy Link

Originally created by @vec715 on GitHub (Apr 11, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15503

What is the issue?

https://ollama.com/blog/mlx

Today, we’re previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple’s machine learning framework.
Get started
Download Ollama 0.19

❯ ollama run hf.co/NexVeridian/gemma-4-31B-it-8bit
pulling manifest
Error: pull model manifest: 400: {"error":"Repository is not GGUF or is not compatible with llama.cpp"}

❯ ollama run hf.co/nvidia/Gemma-4-31B-IT-NVFP4
pulling manifest
Error: pull model manifest: 400: {"error":"Repository is not GGUF or is not compatible with llama.cpp"}

ollama v0.20.5, so why u are confusing people??

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @vec715 on GitHub (Apr 11, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15503 ### What is the issue? https://ollama.com/blog/mlx > Today, we’re previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple’s machine learning framework. Get started Download Ollama 0.19 ❯ ollama run hf.co/NexVeridian/gemma-4-31B-it-8bit pulling manifest Error: pull model manifest: 400: {"error":"Repository is not GGUF or is not compatible with llama.cpp"} ❯ ollama run hf.co/nvidia/Gemma-4-31B-IT-NVFP4 pulling manifest Error: pull model manifest: 400: {"error":"Repository is not GGUF or is not compatible with llama.cpp"} ollama v0.20.5, so why u are confusing people?? ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 20:20:38 -05:00
GiteaMirror commented 2026-04-22 20:20:40 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 11, 2026):

Image
<!-- gh-comment-id:4229614773 --> @rick-github commented on GitHub (Apr 11, 2026): <img width="387" height="116" alt="Image" src="https://github.com/user-attachments/assets/6103c364-58be-4925-a73f-31a1098e9bd5" />
GiteaMirror commented 2026-04-22 20:20:41 -05:00
Author
Owner
Copy Link

@wpostma commented on GitHub (Apr 11, 2026):

So qwen3.5 in nvfp4 format works but NOT other nvfp4 models work YET. Either a different binary of the gemma weights/model or a new version of Ollama, or most likely both, are needed?

<!-- gh-comment-id:4229675212 --> @wpostma commented on GitHub (Apr 11, 2026): So qwen3.5 in nvfp4 format works but NOT other nvfp4 models work YET. Either a different binary of the gemma weights/model or a new version of Ollama, or most likely both, are needed?
GiteaMirror commented 2026-04-22 20:20:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 11, 2026):

This preview release of Ollama accelerates the new Qwen3.5-35B-A3B model, with sampling parameters tuned for coding tasks.

Gemma4 support is in the process of being added. Support for other models will be added as the preview matures.

<!-- gh-comment-id:4229680607 --> @rick-github commented on GitHub (Apr 11, 2026): > This preview release of Ollama accelerates the new [Qwen3.5-35B-A3B](https://ollama.com/library/qwen3.5) model, with sampling parameters tuned for coding tasks. Gemma4 support is in the process of being [added](https://github.com/ollama/ollama/pull/15244). Support for other models will be added as the preview matures.
GiteaMirror commented 2026-04-22 20:20:43 -05:00
Author
Owner
Copy Link

@wpostma commented on GitHub (Apr 11, 2026):

Confirmed works.

% ollama ps
NAME                            ID              SIZE     PROCESSOR    CONTEXT    UNTIL              
qwen3.5:35b-a3b-coding-nvfp4    6e73b30f8f1c    21 GB    100% GPU     262144     4 minutes from now

On my m1 max mac studio 32gb unified memory. tahoe 26.3 os.

<!-- gh-comment-id:4229686246 --> @wpostma commented on GitHub (Apr 11, 2026): Confirmed works. ``` % ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL qwen3.5:35b-a3b-coding-nvfp4 6e73b30f8f1c 21 GB 100% GPU 262144 4 minutes from now ``` On my m1 max mac studio 32gb unified memory. tahoe 26.3 os.
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#35669
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?