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 #12449] "qwen3-embedding:latest" does not support generate #8272

New Issue
Closed
opened 2026-04-12 20:48:50 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 20:48:50 -05:00
Owner
Copy Link

Originally created by @saad039 on GitHub (Sep 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12449

What is the issue?

I'm running ollama inside docker and I'm unable to run the latest Qwen3 embedding model on my machine.

Steps to reproduce

docker run --gpus all -it -v ollama:/root/.ollama ollama/ollama

## docker exec into the running container 

ollama run qwen3-embedding:latest

I've even tried loading the model after running ollama serve. Same output there.

Specs

GPU: NVIDIA GeForce RTX 4060 (mobile)
CPU: Intel i7-14650HX
OS: Arch Linux
Kernel: 6.12.48-1-lts

Relevant log output

root@3d0500d308fe:/# ollama run qwen3-embedding:latest
Error: 400 Bad Request: "qwen3-embedding:latest" does not support generate

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.12.3

Originally created by @saad039 on GitHub (Sep 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12449 ### What is the issue? I'm running ollama inside docker and I'm unable to run the latest Qwen3 embedding model on my machine. ## Steps to reproduce ```bash docker run --gpus all -it -v ollama:/root/.ollama ollama/ollama ## docker exec into the running container ollama run qwen3-embedding:latest ``` I've even tried loading the model after running `ollama serve`. Same output there. ## Specs GPU: NVIDIA GeForce RTX 4060 (mobile) CPU: Intel i7-14650HX OS: Arch Linux Kernel: 6.12.48-1-lts ### Relevant log output ```shell root@3d0500d308fe:/# ollama run qwen3-embedding:latest Error: 400 Bad Request: "qwen3-embedding:latest" does not support generate ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.3
GiteaMirror added the bug label 2026-04-12 20:48:50 -05:00
GiteaMirror commented 2026-04-12 20:48:53 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Sep 29, 2025):

yes qwen3-embedding is not a text generation model so it doesn't support generate. try qwen3:0.6b or qwen3:4b if you're vram constrained

<!-- gh-comment-id:3349375457 --> @mxyng commented on GitHub (Sep 29, 2025): yes qwen3-embedding is not a text generation model so it doesn't support generate. try qwen3:0.6b or qwen3:4b if you're vram constrained
GiteaMirror commented 2026-04-12 20:48:54 -05:00
Author
Owner
Copy Link

@saad039 commented on GitHub (Sep 29, 2025):

It's an embedding model and that's exactly the purpose I want to use it for. It's listed as an available embedding model on ollama's docs.

If I'm missing something, let me know.

<!-- gh-comment-id:3349393132 --> @saad039 commented on GitHub (Sep 29, 2025): It's an embedding model and that's exactly the purpose I want to use it for. It's listed as an available embedding model on ollama's [docs](https://ollama.com/library/qwen3-embedding/tags). If I'm missing something, let me know.
GiteaMirror commented 2026-04-12 20:48:56 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Sep 29, 2025):

you need to use the embedding api. there's no analog in the cli so you can't ollama run it.

try this

curl -s localhost:11434/api/embed -d '{"model":"qwen3-embedding","input":"embed me!"}'
<!-- gh-comment-id:3349416880 --> @mxyng commented on GitHub (Sep 29, 2025): you need to use the [embedding api](https://docs.ollama.com/api#generate-embeddings). there's no analog in the cli so you can't `ollama run` it. try this ```shell curl -s localhost:11434/api/embed -d '{"model":"qwen3-embedding","input":"embed me!"}' ```
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#8272
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?