github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11703] Conversion GPT-OSS #7746

New Issue
Closed
opened 2026-04-12 19:52:39 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 19:52:39 -05:00
Owner
Copy Link

Originally created by @Jeremy-Developer-Page on GitHub (Aug 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11703

What is the issue?

If I download the safetensor model from Huggingface and I try to convert it with Ollama 11.2 and I set the quantization MXFP4 Ollama gets error because it doesn't support it.

How can I fix this bug?

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

11.2

Originally created by @Jeremy-Developer-Page on GitHub (Aug 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11703 ### What is the issue? If I download the safetensor model from Huggingface and I try to convert it with Ollama 11.2 and I set the quantization MXFP4 Ollama gets error because it doesn't support it. How can I fix this bug? ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 11.2
GiteaMirror added the bug label 2026-04-12 19:52:39 -05:00
GiteaMirror commented 2026-04-12 19:52:40 -05:00
Author
Owner
Copy Link

@Jeremy-Developer-Page commented on GitHub (Aug 5, 2025):

After the update from 11.0 to 11.2 I've got the error: Error: unknown architecture

<!-- gh-comment-id:3156852268 --> @Jeremy-Developer-Page commented on GitHub (Aug 5, 2025): After the update from 11.0 to 11.2 I've got the error: Error: unknown architecture
GiteaMirror commented 2026-04-12 19:52:40 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Aug 5, 2025):

Ollama does not use llama.cpp. We've directly worked with OpenAI to implement the model for accuracy, and we've benchmarked against the reference implementations.

The best way is to download the model directly via Ollama's app or via CLI

Sorry about this!

<!-- gh-comment-id:3156881858 --> @mchiang0610 commented on GitHub (Aug 5, 2025): Ollama does not use llama.cpp. We've directly worked with OpenAI to implement the model for accuracy, and we've benchmarked against the reference implementations. The best way is to download the model directly via Ollama's app or via CLI Sorry about this!
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#7746
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?