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 #13194] Error: 500 Internal Server Error: unable to load model #55236

New Issue
Closed
opened 2026-04-29 08:35:14 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 08:35:14 -05:00
Owner
Copy Link

Originally created by @SergioInToronto on GitHub (Nov 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13194

What is the issue?

  1. Pull model from Hugging Face
  2. Run, crashes
$ ollama run --verbose hf.co/QuantStack/Qwen-Image-Edit-GGUF:Q2_K
Error: 500 Internal Server Error: unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304

Seems like this is the issue from the logs. Problem with the model itself?

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen_image'

Relevant log output

Nov 21 07:52:40 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:40 | 200 |      13.022µs |       127.0.0.1 | HEAD     "/"
Nov 21 07:52:40 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:40 | 200 |       9.062µs |       127.0.0.1 | GET      "/api/ps"
Nov 21 07:52:42 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:42 | 200 |      13.764µs |       127.0.0.1 | HEAD     "/"
Nov 21 07:52:42 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:42 | 200 |    8.784425ms |       127.0.0.1 | GET      "/api/tags"
Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 |      18.829µs |       127.0.0.1 | HEAD     "/"
Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 |    3.954528ms |       127.0.0.1 | POST     "/api/show"
Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 |    2.457067ms |       127.0.0.1 | POST     "/api/show"
Nov 21 07:52:50 RogTop ollama[5985]: time=2025-11-21T07:52:50.075-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43809"
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: loaded meta data with 3 key-value pairs and 1933 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304 (version GGUF V3 (latest))
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv   0:                       general.architecture str              = qwen_image
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv   1:               general.quantization_version u32              = 2
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv   2:                          general.file_type u32              = 10
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type  f32: 1087 tensors
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q2_K:  696 tensors
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q3_K:  116 tensors
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q4_K:   28 tensors
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type bf16:    6 tensors
Nov 21 07:52:50 RogTop ollama[5985]: print_info: file format = GGUF V3 (latest)
Nov 21 07:52:50 RogTop ollama[5985]: print_info: file type   = Q2_K - Medium
Nov 21 07:52:50 RogTop ollama[5985]: print_info: file size   = 6.58 GiB (2.77 BPW)
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen_image'
Nov 21 07:52:50 RogTop ollama[5985]: llama_model_load_from_file_impl: failed to load model
Nov 21 07:52:50 RogTop ollama[5985]: time=2025-11-21T07:52:50.322-05:00 level=INFO source=sched.go:425 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304"
Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 500 |  247.160546ms |       127.0.0.1 | POST     "/api/generate"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.12.11

Originally created by @SergioInToronto on GitHub (Nov 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13194 ### What is the issue? 1. Pull model from Hugging Face 2. Run, crashes ```bash $ ollama run --verbose hf.co/QuantStack/Qwen-Image-Edit-GGUF:Q2_K Error: 500 Internal Server Error: unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304 ``` Seems like this is the issue from the logs. Problem with the model itself? ``` llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen_image' ``` ### Relevant log output ```shell Nov 21 07:52:40 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:40 | 200 | 13.022µs | 127.0.0.1 | HEAD "/" Nov 21 07:52:40 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:40 | 200 | 9.062µs | 127.0.0.1 | GET "/api/ps" Nov 21 07:52:42 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:42 | 200 | 13.764µs | 127.0.0.1 | HEAD "/" Nov 21 07:52:42 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:42 | 200 | 8.784425ms | 127.0.0.1 | GET "/api/tags" Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 | 18.829µs | 127.0.0.1 | HEAD "/" Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 | 3.954528ms | 127.0.0.1 | POST "/api/show" Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 200 | 2.457067ms | 127.0.0.1 | POST "/api/show" Nov 21 07:52:50 RogTop ollama[5985]: time=2025-11-21T07:52:50.075-05:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43809" Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: loaded meta data with 3 key-value pairs and 1933 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304 (version GGUF V3 (latest)) Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv 0: general.architecture str = qwen_image Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv 1: general.quantization_version u32 = 2 Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - kv 2: general.file_type u32 = 10 Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type f32: 1087 tensors Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q2_K: 696 tensors Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q3_K: 116 tensors Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type q4_K: 28 tensors Nov 21 07:52:50 RogTop ollama[5985]: llama_model_loader: - type bf16: 6 tensors Nov 21 07:52:50 RogTop ollama[5985]: print_info: file format = GGUF V3 (latest) Nov 21 07:52:50 RogTop ollama[5985]: print_info: file type = Q2_K - Medium Nov 21 07:52:50 RogTop ollama[5985]: print_info: file size = 6.58 GiB (2.77 BPW) Nov 21 07:52:50 RogTop ollama[5985]: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen_image' Nov 21 07:52:50 RogTop ollama[5985]: llama_model_load_from_file_impl: failed to load model Nov 21 07:52:50 RogTop ollama[5985]: time=2025-11-21T07:52:50.322-05:00 level=INFO source=sched.go:425 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-a3f1680339685f558cbdf0254684e3529aab52b7e37aa8055eed0e8844a2b304" Nov 21 07:52:50 RogTop ollama[5985]: [GIN] 2025/11/21 - 07:52:50 | 500 | 247.160546ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.11
GiteaMirror added the bug label 2026-04-29 08:35:14 -05:00
GiteaMirror commented 2026-04-29 08:35:17 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 21, 2025):

qwen-image-edit is not a supported model.

<!-- gh-comment-id:3562922420 --> @rick-github commented on GitHub (Nov 21, 2025): qwen-image-edit is not a supported model.
GiteaMirror commented 2026-04-29 08:35:18 -05:00
Author
Owner
Copy Link

@SergioInToronto commented on GitHub (Nov 21, 2025):

Thanks @rick-github !

Noob question, how can I tell which models are supported?

<!-- gh-comment-id:3562928394 --> @SergioInToronto commented on GitHub (Nov 21, 2025): Thanks @rick-github ! Noob question, how can I tell which models are supported?
GiteaMirror commented 2026-04-29 08:35:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 21, 2025):

The source of truth is the ollama library: https://ollama.com/library. Any models from other sources (HuggingFace, ModelScope) etc that are based on models (finetuned, modified system message, etc) that are in the ollama library have a high likelihood of working with ollama. Models with a unique architecture may not be supported but could be some time in the future. Also note that ollama currently only supports two modalities - text to text and image to text. Models like qwen-image-edit, image to image, require changes to the API as well as model specific changes so support is further away than say gemma4.

<!-- gh-comment-id:3562951673 --> @rick-github commented on GitHub (Nov 21, 2025): The source of truth is the ollama library: https://ollama.com/library. Any models from other sources (HuggingFace, ModelScope) etc that are based on models (finetuned, modified system message, etc) that are in the ollama library have a high likelihood of working with ollama. Models with a unique architecture may not be supported but could be some time in the future. Also note that ollama currently only supports two modalities - text to text and image to text. Models like qwen-image-edit, image to image, require changes to the API as well as model specific changes so support is further away than say gemma4.
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#55236
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?