github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13262] The latest version of ollama cannot deploy the qwen3-instruct model that I fine-tuned. #55280

New Issue
Closed
opened 2026-04-29 08:43:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 08:43:33 -05:00
Owner
Copy Link

Originally created by @diemeng9339 on GitHub (Nov 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13262

What is the issue?

The latest version of ollama cannot deploy the qwen3-instruct model that I fine-tuned. However, it can deploy the qwen2.5 fine-tuned model;
I hope it can be fixed as soon as possible, and the fine-tuned qwen3 model can be supported for deployment。

Relevant log output

gathering model components
copying file sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 100%
copying file sha256:8f960059b84df8a646d13d99fa6977e13a65f8d7425cb482ea9a589be88291e6 100%
copying file sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 100%
copying file sha256:74e923dd507a5ecec8d596353290ca705ef8e4b7191d5823bbd4b77040515012 100%
copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100%
copying file sha256:06b3d5319b6d76d1a4a2433419180016cfd54ed62d086a5e6567a809f8c82634 100%
copying file sha256:4d9818c3d27895c0058828a5f68bc7a4de80c3ae1bcdac90936ce24178063f59 100%
copying file sha256:d1bd7a5054d40eec2b985f1c8614655000e7508ccfff556d7010ee8ce7e5e09f 100%
copying file sha256:a1b720596397d3a29ba3fd219fb1e0e5361b37591217be66a2a18d66f9031264 100%
copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100%
converting model
Error: unsupported architecture "Qwen3ForCausalLM"

OS

Windows

GPU

No response

CPU

Intel

Ollama version

0.13.0

Originally created by @diemeng9339 on GitHub (Nov 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13262 ### What is the issue? The latest version of ollama cannot deploy the qwen3-instruct model that I fine-tuned. However, it can deploy the qwen2.5 fine-tuned model; I hope it can be fixed as soon as possible, and the fine-tuned qwen3 model can be supported for deployment。 ### Relevant log output ```shell gathering model components copying file sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 100% copying file sha256:8f960059b84df8a646d13d99fa6977e13a65f8d7425cb482ea9a589be88291e6 100% copying file sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 100% copying file sha256:74e923dd507a5ecec8d596353290ca705ef8e4b7191d5823bbd4b77040515012 100% copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% copying file sha256:06b3d5319b6d76d1a4a2433419180016cfd54ed62d086a5e6567a809f8c82634 100% copying file sha256:4d9818c3d27895c0058828a5f68bc7a4de80c3ae1bcdac90936ce24178063f59 100% copying file sha256:d1bd7a5054d40eec2b985f1c8614655000e7508ccfff556d7010ee8ce7e5e09f 100% copying file sha256:a1b720596397d3a29ba3fd219fb1e0e5361b37591217be66a2a18d66f9031264 100% copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% converting model Error: unsupported architecture "Qwen3ForCausalLM" ``` ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version 0.13.0
GiteaMirror added the bug label 2026-04-29 08:43:33 -05:00
GiteaMirror commented 2026-04-29 08:43:39 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 28, 2025):

The import process only handles a subset of model architectures, Qwen3ForCausalLM is not one of them. Use llama.cpp to convert to GGUF and import that.

<!-- gh-comment-id:3588549139 --> @rick-github commented on GitHub (Nov 28, 2025): The import process only handles a subset of [model architectures](https://github.com/ollama/ollama/blob/main/docs/import.mdx#importing-a-model-from-safetensors-weights), Qwen3ForCausalLM is not one of them. Use llama.cpp to convert to GGUF and import that.
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#55280
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?