github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #16014] nemotron3:33b fails to load with 'unknown architecture' error #87883

New Issue
Closed
opened 2026-05-10 06:30:10 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-10 06:30:10 -05:00
Owner
Copy Link

Originally created by @ulope on GitHub (May 6, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/16014

What is the issue?

Trying to run nemotron3:33b on ollama/ollama:0.17.6-rocm (docker) gives the following error: unknown model architecture: 'nemotron_h_omni'

Relevant log output

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'nemotron_h_omni'
llama_model_load_from_file_impl: failed to load model
time=2026-05-06T13:58:48.561Z level=INFO source=sched.go:471 msg="NewLlamaServer failed" model=/root/.ollama/models/blobs/sha256-02025860dddec7ec009768f05966d941e0a89b470e805e136018149d1dabcf26 error="unable to load model: /root/.ollama/models/blobs/sha256-02025860dddec7ec009768f05966d941e0a89b470e805e136018149d1dabcf26"

OS

Docker

GPU

AMD

CPU

AMD

Ollama version

0.17.6-rocm

Originally created by @ulope on GitHub (May 6, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/16014 ### What is the issue? Trying to run `nemotron3:33b` on `ollama/ollama:0.17.6-rocm` (docker) gives the following error: `unknown model architecture: 'nemotron_h_omni'` ### Relevant log output ```shell llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'nemotron_h_omni' llama_model_load_from_file_impl: failed to load model time=2026-05-06T13:58:48.561Z level=INFO source=sched.go:471 msg="NewLlamaServer failed" model=/root/.ollama/models/blobs/sha256-02025860dddec7ec009768f05966d941e0a89b470e805e136018149d1dabcf26 error="unable to load model: /root/.ollama/models/blobs/sha256-02025860dddec7ec009768f05966d941e0a89b470e805e136018149d1dabcf26" ``` ### OS Docker ### GPU AMD ### CPU AMD ### Ollama version 0.17.6-rocm
GiteaMirror added the bug label 2026-05-10 06:30:10 -05:00
GiteaMirror commented 2026-05-10 06:30:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 6, 2026):

Upgrade ollama. nemotron_h_omni architecture is supported from 0.22.0.

<!-- gh-comment-id:4389673614 --> @rick-github commented on GitHub (May 6, 2026): Upgrade ollama. nemotron_h_omni architecture is supported from [0.22.0](https://github.com/ollama/ollama/releases/tag/v0.22.0).
GiteaMirror commented 2026-05-10 06:30:13 -05:00
Author
Owner
Copy Link

@ulope commented on GitHub (May 6, 2026):

Doh, I was quite sure I had upgraded before trying the model.

Sorry for the noise.

<!-- gh-comment-id:4389985103 --> @ulope commented on GitHub (May 6, 2026): Doh, I was quite sure I had upgraded before trying the model. Sorry for the noise.
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#87883
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?