github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12447] Embedding models don't seem to be working. #54783

New Issue
Closed
opened 2026-04-29 07:18:14 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 07:18:14 -05:00
Owner
Copy Link

Originally created by @AZComputerSolutions on GitHub (Sep 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12447

Originally assigned to: @mxyng on GitHub.

What is the issue?

Whenever I try to use embedding ,it seems to come back with an erorr:

Here is the discord topic talking about it: https://discord.com/channels/1128867683291627614/1419072966922211429/1419072966922211429

This is happening with gpt-oss-20b and a ton of other models I have tried (which I have used and had no problem until after the recent upgrade of ollama). It seems like none of the models via the ollama download is working. The workaround via the Discord message thread above seems to work, but it obviously will not work via Cloud, which I am trying to use.

Relevant log output

time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:487 msg="offloading 10 repeating layers to GPU"
time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:491 msg="offloading output layer to CPU"
time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:498 msg="offloaded 10/25 layers to GPU"
time=2025-09-29T13:17:58.713-06:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="4.4 GiB"
time=2025-09-29T13:17:58.714-06:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="8.4 GiB"
time=2025-09-29T13:17:58.714-06:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="85.0 MiB"
time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:326 msg="kv cache" device=CPU size="119.0 MiB"
time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="126.8 MiB"
time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="109.2 MiB"
time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:342 msg="total memory" size="13.3 GiB"
time=2025-09-29T13:17:58.715-06:00 level=INFO source=sched.go:470 msg="loaded runners" count=1
time=2025-09-29T13:17:58.715-06:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding"
time=2025-09-29T13:17:58.719-06:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model"
time=2025-09-29T13:18:06.370-06:00 level=INFO source=server.go:1289 msg="llama runner started in 11.86 seconds"
time=2025-09-29T13:18:06.569-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.573-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.576-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.580-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.583-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.586-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.590-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.592-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.596-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:06.600-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
[GIN] 2025/09/29 - 13:18:06 | 500 |   22.5008328s |       10.5.1.76 | POST     "/api/embed"
time=2025-09-29T13:18:24.820-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.827-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.833-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.841-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.846-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.853-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.859-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.865-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.871-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:18:24.877-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
[GIN] 2025/09/29 - 13:18:24 | 500 |    900.7491ms |       10.5.1.76 | POST     "/api/embed"
time=2025-09-29T13:19:26.343-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.350-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.357-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.363-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.370-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.376-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.382-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.388-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.394-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"
time=2025-09-29T13:19:26.401-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.3

Originally created by @AZComputerSolutions on GitHub (Sep 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12447 Originally assigned to: @mxyng on GitHub. ### What is the issue? Whenever I try to use embedding ,it seems to come back with an erorr: Here is the discord topic talking about it: https://discord.com/channels/1128867683291627614/1419072966922211429/1419072966922211429 This is happening with gpt-oss-20b and a ton of other models I have tried (which I have used and had no problem until after the recent upgrade of ollama). It seems like none of the models via the ollama download is working. The workaround via the Discord message thread above seems to work, but it obviously will not work via Cloud, which I am trying to use. ### Relevant log output ```shell time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:487 msg="offloading 10 repeating layers to GPU" time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:491 msg="offloading output layer to CPU" time=2025-09-29T13:17:58.711-06:00 level=INFO source=ggml.go:498 msg="offloaded 10/25 layers to GPU" time=2025-09-29T13:17:58.713-06:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="4.4 GiB" time=2025-09-29T13:17:58.714-06:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="8.4 GiB" time=2025-09-29T13:17:58.714-06:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="85.0 MiB" time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:326 msg="kv cache" device=CPU size="119.0 MiB" time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="126.8 MiB" time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="109.2 MiB" time=2025-09-29T13:17:58.715-06:00 level=INFO source=backend.go:342 msg="total memory" size="13.3 GiB" time=2025-09-29T13:17:58.715-06:00 level=INFO source=sched.go:470 msg="loaded runners" count=1 time=2025-09-29T13:17:58.715-06:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding" time=2025-09-29T13:17:58.719-06:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model" time=2025-09-29T13:18:06.370-06:00 level=INFO source=server.go:1289 msg="llama runner started in 11.86 seconds" time=2025-09-29T13:18:06.569-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.573-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.576-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.580-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.583-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.586-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.590-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.592-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.596-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:06.600-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" [GIN] 2025/09/29 - 13:18:06 | 500 | 22.5008328s | 10.5.1.76 | POST "/api/embed" time=2025-09-29T13:18:24.820-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.827-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.833-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.841-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.846-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.853-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.859-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.865-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.871-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:18:24.877-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" [GIN] 2025/09/29 - 13:18:24 | 500 | 900.7491ms | 10.5.1.76 | POST "/api/embed" time=2025-09-29T13:19:26.343-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.350-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.357-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.363-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.370-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.376-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.382-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.388-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.394-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" time=2025-09-29T13:19:26.401-06:00 level=INFO source=server.go:1598 msg="llm embedding error: this model does not support embeddings" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.3
GiteaMirror added the bug label 2026-04-29 07:18:14 -05:00
GiteaMirror commented 2026-04-29 07:18:16 -05:00
Author
Owner
Copy Link

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

since you didn't link the model, I'm going to assume it's gpt-oss:20b. this model is a text generation model. as such, we don't support generating embeddings for this model. for embeddings, you should use a dedicated embedding model such as embeddinggemma or qwen3 embedding

<!-- gh-comment-id:3349022364 --> @mxyng commented on GitHub (Sep 29, 2025): since you didn't link the model, I'm going to assume it's [gpt-oss:20b](https://ollama.com/library/gpt-oss:20b). this model is a text generation model. as such, we don't support generating embeddings for this model. for embeddings, you should use a dedicated embedding model such as [embeddinggemma](https://ollama.com/library/embeddinggemma) or [qwen3 embedding](https://ollama.com/library/qwen3-embedding)
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#54783
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?