github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4063] moondream returns no response #49034

New Issue
Closed
opened 2026-04-28 10:37:24 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-28 10:37:24 -05:00
Owner
Copy Link

Originally created by @DuckyBlender on GitHub (Apr 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4063

What is the issue?

moondream model and other vision models like phi3 llava doesn’t return any text most of the time. Running Ollama 0.1.33-pre5 and ollama-rs. Not an issue with ollama-rs because I tried in the CLI and it also returned nothing.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.33-pre5

Originally created by @DuckyBlender on GitHub (Apr 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4063 ### What is the issue? moondream model and other vision models like phi3 llava doesn’t return any text most of the time. Running Ollama 0.1.33-pre5 and ollama-rs. Not an issue with ollama-rs because I tried in the CLI and it also returned nothing. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.33-pre5
GiteaMirror added the bug label 2026-04-28 10:37:24 -05:00
GiteaMirror commented 2026-04-28 10:37:25 -05:00
Author
Owner
Copy Link

@rb81 commented on GitHub (May 1, 2024):

Maybe related to: https://github.com/ollama/ollama/issues/4076

<!-- gh-comment-id:2088338621 --> @rb81 commented on GitHub (May 1, 2024): Maybe related to: https://github.com/ollama/ollama/issues/4076
GiteaMirror commented 2026-04-28 10:37:25 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 2, 2024):

Maybe related to: #4076

Nope, running ollama pre-release which should support moondream. I just get no response. If I ask it about the image on the next chat turn it works...

<!-- gh-comment-id:2090105201 --> @DuckyBlender commented on GitHub (May 2, 2024): > Maybe related to: #4076 Nope, running ollama pre-release which should support moondream. I just get no response. If I ask it about the image on the next chat turn it works...
GiteaMirror commented 2026-04-28 10:37:26 -05:00
Author
Owner
Copy Link

@rvalieris commented on GitHub (May 4, 2024):

same issue here on the release 0.1.33, running on linux cpu only.

running ollama run 'moondream:1.8b' '', ollama serve prints:

[....]
clip_model_load: params backend buffer size =  867.61 MB (457 tensors)
key clip.vision.image_grid_pinpoints not found in file
key clip.vision.mm_patch_merge_type not found in file
key clip.vision.image_crop_resolution not found in file
clip_model_load: failed to load vision model tensors
time=2024-05-04T11:04:28.884-03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 "
<!-- gh-comment-id:2094215785 --> @rvalieris commented on GitHub (May 4, 2024): same issue here on the release 0.1.33, running on linux cpu only. running `ollama run 'moondream:1.8b' ''`, ollama serve prints: ``` [....] clip_model_load: params backend buffer size = 867.61 MB (457 tensors) key clip.vision.image_grid_pinpoints not found in file key clip.vision.mm_patch_merge_type not found in file key clip.vision.image_crop_resolution not found in file clip_model_load: failed to load vision model tensors time=2024-05-04T11:04:28.884-03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 " ```
GiteaMirror commented 2026-04-28 10:37:26 -05:00
Author
Owner
Copy Link

@rvalieris commented on GitHub (May 4, 2024):

nevermind, a few hours ago the archlinux package updated (0.1.33-2 -> 0.1.33-4) and now it works, I'm not sure what changed but it seems it was a packaging issue in my case.

<!-- gh-comment-id:2094287906 --> @rvalieris commented on GitHub (May 4, 2024): nevermind, a few hours ago the archlinux package updated (0.1.33-2 -> 0.1.33-4) and now it works, I'm not sure what changed but it seems it was a packaging issue in my case.
GiteaMirror commented 2026-04-28 10:37:27 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 5, 2024):

duplicate of #4163

<!-- gh-comment-id:2094908457 --> @DuckyBlender commented on GitHub (May 5, 2024): duplicate of #4163
GiteaMirror commented 2026-04-28 10:37:27 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 5, 2024):

nevermind, a few hours ago the archlinux package updated (0.1.33-2 -> 0.1.33-4) and now it works, I'm not sure what changed but it seems it was a packaging issue in my case.

are you sure it's working? #4163 suggests this is an active issue

<!-- gh-comment-id:2094908744 --> @DuckyBlender commented on GitHub (May 5, 2024): > nevermind, a few hours ago the archlinux package updated (0.1.33-2 -> 0.1.33-4) and now it works, I'm not sure what changed but it seems it was a packaging issue in my case. are you sure it's working? #4163 suggests this is an active issue
GiteaMirror commented 2026-04-28 10:37:27 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 5, 2024):

same issue here on the release 0.1.33, running on linux cpu only.

running ollama run 'moondream:1.8b' '', ollama serve prints:

[....]
clip_model_load: params backend buffer size =  867.61 MB (457 tensors)
key clip.vision.image_grid_pinpoints not found in file
key clip.vision.mm_patch_merge_type not found in file
key clip.vision.image_crop_resolution not found in file
clip_model_load: failed to load vision model tensors
time=2024-05-04T11:04:28.884-03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 "

oh, this isn't even my error. my model loads but doesn't respond anything. if i ask it on the next turn it works

<!-- gh-comment-id:2094910290 --> @DuckyBlender commented on GitHub (May 5, 2024): > same issue here on the release 0.1.33, running on linux cpu only. > > running `ollama run 'moondream:1.8b' ''`, ollama serve prints: > > ``` > [....] > clip_model_load: params backend buffer size = 867.61 MB (457 tensors) > key clip.vision.image_grid_pinpoints not found in file > key clip.vision.mm_patch_merge_type not found in file > key clip.vision.image_crop_resolution not found in file > clip_model_load: failed to load vision model tensors > time=2024-05-04T11:04:28.884-03:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 " > ``` oh, this isn't even my error. my model loads but doesn't respond anything. if i ask it on the next turn it works
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#49034
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?