github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-10 10:41:01 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13044] qwen3-vl:30b-a3b-instruct-q8_0 Image recognition error #8643

New Issue
Closed
opened 2026-04-12 21:22:58 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 21:22:58 -05:00
Owner
Copy Link

Originally created by @rikthhpgf2005 on GitHub (Nov 11, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13044

What is the issue?

qwen3-vl:30b-a3b-instruct-q8_0 Image recognition error

Image

Relevant log output

[GIN] 2025/11/11 - 11:55:20 | 500 |     53.0585ms |             ::1 | POST     "/v1/chat/completions"
time=2025-11-11T11:55:23.156+08:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:5112: height:23 or width:237 must be larger than factor:32\ngoroutine 1623 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x7ff64bffe820?, 0xc000eee700?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).SmartResize(0x7ff64c39a800?, 0xc0001a6c80?, 0xed)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:54 +0x3e7\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).ProcessImage(0xc000ebf560, {0x7ff64c3a74e0, 0xc0001a6c40}, {0x7ff64c39a800?, 0xc0001a6c80?})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:92 +0x9c\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000ebf520, {0x7ff64c3a74e0, 0xc0001a6c40}, {0xc00189c000, 0x3a3, 0x3a5})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:37 +0x113\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).inputs(0xc00073a5a0, {0xc0000e6790, 0xaa}, {0xc0001a6b00, 0x2, 0xc000100808?})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:247 +0x50a\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).NewSequence(0xc00073a5a0, {0xc0000e6790, 0xaa}, {0xc0001a6b00, 0x2, 0x2}, {0xa000, {0x0, 0x0, 0x0}, ...})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:119 +0x8f\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00073a5a0, {0x7ff64c399e90, 0xc0006b9180}, 0xc00052af00)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:847 +0x5c9\nnet/http.HandlerFunc.ServeHTTP(0xc00072fa40?, {0x7ff64c399e90?, 0xc0006b9180?}, 0xc0013c1b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x7ff64ae6b785?, {0x7ff64c399e90, 0xc0006b9180}, 0xc00052af00)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x7ff64c396410?}, {0x7ff64c399e90?, 0xc0006b9180?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc000628e10, {0x7ff64c39c218, 0xc000624c90})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485"
time=2025-11-11T11:55:23.157+08:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:4583/completion\": EOF"
[GIN] 2025/11/11 - 11:55:23 | 500 |     57.3045ms |             ::1 | POST     "/v1/chat/completions"
time=2025-11-11T11:55:27.471+08:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:5134: height:23 or width:237 must be larger than factor:32\ngoroutine 1597 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x7ff64bffe820?, 0xc000eee850?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).SmartResize(0x7ff64c39a800?, 0xc0001a6e80?, 0xed)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:54 +0x3e7\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).ProcessImage(0xc000ebf560, {0x7ff64c3a74e0, 0xc0001a6e40}, {0x7ff64c39a800?, 0xc0001a6e80?})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:92 +0x9c\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000ebf520, {0x7ff64c3a74e0, 0xc0001a6e40}, {0xc00189c800, 0x3a3, 0x3a5})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:37 +0x113\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).inputs(0xc00073a5a0, {0xc0000d6460, 0xa0}, {0xc000f43620, 0x1, 0xc0006cd008?})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:247 +0x50a\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).NewSequence(0xc00073a5a0, {0xc0000d6460, 0xa0}, {0xc000f43620, 0x1, 0x1}, {0xa000, {0x0, 0x0, 0x0}, ...})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:119 +0x8f\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00073a5a0, {0x7ff64c399e90, 0xc0006b95e0}, 0xc00052b2c0)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:847 +0x5c9\nnet/http.HandlerFunc.ServeHTTP(0xc00072fa40?, {0x7ff64c399e90?, 0xc0006b95e0?}, 0xc000f93b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x7ff64ae6b785?, {0x7ff64c399e90, 0xc0006b95e0}, 0xc00052b2c0)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x7ff64c396410?}, {0x7ff64c399e90?, 0xc0006b95e0?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc000356510, {0x7ff64c39c218, 0xc000624c90})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485"
time=2025-11-11T11:55:27.471+08:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:4583/completion\": EOF"
[GIN] 2025/11/11 - 11:55:27 | 500 |     52.8734ms |             ::1 | POST     "/v1/chat/completions"

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

v0.12.10

Originally created by @rikthhpgf2005 on GitHub (Nov 11, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13044 ### What is the issue? qwen3-vl:30b-a3b-instruct-q8_0 Image recognition error <img width="1126" height="679" alt="Image" src="https://github.com/user-attachments/assets/cee3150e-7a98-403d-8bb8-f172135eec01" /> ### Relevant log output ```shell [GIN] 2025/11/11 - 11:55:20 | 500 | 53.0585ms | ::1 | POST "/v1/chat/completions" time=2025-11-11T11:55:23.156+08:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:5112: height:23 or width:237 must be larger than factor:32\ngoroutine 1623 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x7ff64bffe820?, 0xc000eee700?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).SmartResize(0x7ff64c39a800?, 0xc0001a6c80?, 0xed)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:54 +0x3e7\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).ProcessImage(0xc000ebf560, {0x7ff64c3a74e0, 0xc0001a6c40}, {0x7ff64c39a800?, 0xc0001a6c80?})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:92 +0x9c\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000ebf520, {0x7ff64c3a74e0, 0xc0001a6c40}, {0xc00189c000, 0x3a3, 0x3a5})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:37 +0x113\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).inputs(0xc00073a5a0, {0xc0000e6790, 0xaa}, {0xc0001a6b00, 0x2, 0xc000100808?})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:247 +0x50a\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).NewSequence(0xc00073a5a0, {0xc0000e6790, 0xaa}, {0xc0001a6b00, 0x2, 0x2}, {0xa000, {0x0, 0x0, 0x0}, ...})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:119 +0x8f\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00073a5a0, {0x7ff64c399e90, 0xc0006b9180}, 0xc00052af00)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:847 +0x5c9\nnet/http.HandlerFunc.ServeHTTP(0xc00072fa40?, {0x7ff64c399e90?, 0xc0006b9180?}, 0xc0013c1b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x7ff64ae6b785?, {0x7ff64c399e90, 0xc0006b9180}, 0xc00052af00)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x7ff64c396410?}, {0x7ff64c399e90?, 0xc0006b9180?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc000628e10, {0x7ff64c39c218, 0xc000624c90})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485" time=2025-11-11T11:55:23.157+08:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:4583/completion\": EOF" [GIN] 2025/11/11 - 11:55:23 | 500 | 57.3045ms | ::1 | POST "/v1/chat/completions" time=2025-11-11T11:55:27.471+08:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:5134: height:23 or width:237 must be larger than factor:32\ngoroutine 1597 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x7ff64bffe820?, 0xc000eee850?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).SmartResize(0x7ff64c39a800?, 0xc0001a6e80?, 0xed)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:54 +0x3e7\ngithub.com/ollama/ollama/model/models/qwen3vl.(*ImageProcessor).ProcessImage(0xc000ebf560, {0x7ff64c3a74e0, 0xc0001a6e40}, {0x7ff64c39a800?, 0xc0001a6e80?})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/imageprocessor.go:92 +0x9c\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000ebf520, {0x7ff64c3a74e0, 0xc0001a6e40}, {0xc00189c800, 0x3a3, 0x3a5})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:37 +0x113\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).inputs(0xc00073a5a0, {0xc0000d6460, 0xa0}, {0xc000f43620, 0x1, 0xc0006cd008?})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:247 +0x50a\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).NewSequence(0xc00073a5a0, {0xc0000d6460, 0xa0}, {0xc000f43620, 0x1, 0x1}, {0xa000, {0x0, 0x0, 0x0}, ...})\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:119 +0x8f\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc00073a5a0, {0x7ff64c399e90, 0xc0006b95e0}, 0xc00052b2c0)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:847 +0x5c9\nnet/http.HandlerFunc.ServeHTTP(0xc00072fa40?, {0x7ff64c399e90?, 0xc0006b95e0?}, 0xc000f93b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x7ff64ae6b785?, {0x7ff64c399e90, 0xc0006b95e0}, 0xc00052b2c0)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x7ff64c396410?}, {0x7ff64c399e90?, 0xc0006b95e0?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc000356510, {0x7ff64c39c218, 0xc000624c90})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485" time=2025-11-11T11:55:27.471+08:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:4583/completion\": EOF" [GIN] 2025/11/11 - 11:55:27 | 500 | 52.8734ms | ::1 | POST "/v1/chat/completions" ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version v0.12.10
GiteaMirror added the bugneeds more info labels 2026-04-12 21:22:58 -05:00
GiteaMirror commented 2026-04-12 21:22:59 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 11, 2025):

The image is too narrow to be processed by the model. Either resize it so that it is at least 32 pixels in height, or capture a new screenshot that has a height of 32 pixels or more.

<!-- gh-comment-id:3515328464 --> @rick-github commented on GitHub (Nov 11, 2025): The image is too narrow to be processed by the model. Either resize it so that it is at least 32 pixels in height, or capture a new screenshot that has a height of 32 pixels or more.
GiteaMirror commented 2026-04-12 21:23:00 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 12, 2025):

@rikthhpgf2005 can you report back if that works?

<!-- gh-comment-id:3519296745 --> @pdevine commented on GitHub (Nov 12, 2025): @rikthhpgf2005 can you report back if that works?
GiteaMirror commented 2026-04-12 21:23:00 -05:00
Author
Owner
Copy Link

@rikthhpgf2005 commented on GitHub (Nov 12, 2025):

Image Image
<!-- gh-comment-id:3521510038 --> @rikthhpgf2005 commented on GitHub (Nov 12, 2025): <img width="895" height="952" alt="Image" src="https://github.com/user-attachments/assets/a33e105d-f20e-48f5-9880-103dea696f01" /> <img width="355" height="186" alt="Image" src="https://github.com/user-attachments/assets/0b1f3731-6e07-46cf-8bbe-a34bd0f744d9" />
GiteaMirror commented 2026-04-12 21:23:00 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 12, 2025):

Can you post the log from this failure?

<!-- gh-comment-id:3521683667 --> @rick-github commented on GitHub (Nov 12, 2025): Can you post the log from this failure?
GiteaMirror commented 2026-04-12 21:23:01 -05:00
Author
Owner
Copy Link

@rikthhpgf2005 commented on GitHub (Nov 12, 2025):

A failed small image upload, combined with not clearing the context, led to 500 errors for all subsequent images. Restarting ollama after clearing the context fixed the issue.

<!-- gh-comment-id:3521719243 --> @rikthhpgf2005 commented on GitHub (Nov 12, 2025): A failed small image upload, combined with not clearing the context, led to 500 errors for all subsequent images. Restarting ollama after clearing the context fixed the issue.
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 needs more info
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#8643
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?