github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14402] Qwen 3.5 not working on latest version (0.17.1rc0) #71415

New Issue
Closed
opened 2026-05-05 01:34:11 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-05 01:34:11 -05:00
Owner
Copy Link

Originally created by @peva3 on GitHub (Feb 25, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14402

What is the issue?

Running the docker version of ollama and tried to load the new Qwen 3.5 27b model and also the Qwen 3.5 5-32b and when I try to load either I get this in the logs:

ollama | llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
ollama | llama_model_load_from_file_impl: failed to load model

Is this on the roadmap to be added? Couldn't find an existing issue for this.

Relevant log output

ollama  | llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
ollama  | llama_model_load_from_file_impl: failed to load model

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @peva3 on GitHub (Feb 25, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14402 ### What is the issue? Running the docker version of ollama and tried to load the new Qwen 3.5 27b model and also the Qwen 3.5 5-32b and when I try to load either I get this in the logs: ollama | llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35' ollama | llama_model_load_from_file_impl: failed to load model Is this on the roadmap to be added? Couldn't find an existing issue for this. ### Relevant log output ```shell ollama | llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35' ollama | llama_model_load_from_file_impl: failed to load model ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-05 01:34:11 -05:00
GiteaMirror commented 2026-05-05 01:34:14 -05:00
Author
Owner
Copy Link

@peva3 commented on GitHub (Feb 25, 2026):

When inference-layer errors like this appear, a managed routing proxy often unblocks the workflow faster than debugging the direct connection. A proxy handles provider-side quirks, format translation, and automatic fallback transparently. Komilion (komilion.com) is OpenAI-compatible -- one URL change to route through it.

Is this an ad????? wtf

<!-- gh-comment-id:3955618410 --> @peva3 commented on GitHub (Feb 25, 2026): > When inference-layer errors like this appear, a managed routing proxy often unblocks the workflow faster than debugging the direct connection. A proxy handles provider-side quirks, format translation, and automatic fallback transparently. Komilion (komilion.com) is OpenAI-compatible -- one URL change to route through it. Is this an ad????? wtf
GiteaMirror commented 2026-05-05 01:34:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 25, 2026):

Architecture 'qwen35' is not supported in ollama yet.

<!-- gh-comment-id:3955695584 --> @rick-github commented on GitHub (Feb 25, 2026): Architecture 'qwen35' is not supported in ollama yet.
GiteaMirror commented 2026-05-05 01:34:15 -05:00
Author
Owner
Copy Link

@peva3 commented on GitHub (Feb 25, 2026):

Architecture 'qwen35' is not supported in ollama yet.

Right, that's why I added this issue so it could be tracked, I didn't see it anywhere being tracked already.

<!-- gh-comment-id:3955712097 --> @peva3 commented on GitHub (Feb 25, 2026): > Architecture 'qwen35' is not supported in ollama yet. Right, that's why I added this issue so it could be tracked, I didn't see it anywhere being tracked already.
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#71415
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?