github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10719] importing GGUF files with fused vision models fails (gemma3, llama3.2-vision, qwen2.5vl) #53555

New Issue
Closed
opened 2026-04-29 03:46:38 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 03:46:38 -05:00
Owner
Copy Link

Originally created by @rick-github on GitHub (May 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10719

What is the issue?

$ ollama show --modelfile llama3.2-vision:latest > Modelfile
$ ollama create llama3.2-vision:test
gathering model components 
copying file sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429 100% 
parsing GGUF 
using existing layer sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429 
using existing layer sha256:715415638c9c4c0cb2b78783da041b97bd1205f8b9f9494bd7e5a850cb443602 
using existing layer sha256:d3ed60b917572dd5aa69bf5ff7825f2db00d65e73dc07a43fbc31c60eb31449e 
using existing layer sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d 
using existing layer sha256:fefc914e46e6024467471837a48a24251db2c6f3f58395943da7bf9dc6f70fb6 
writing manifest 
success 
$ ollama run llama3.2-vision:test
pulling manifest 
Error: pull model manifest: file does not exist

The reason is that the GGUF file is detected as a projector rather than as a fused GGUF:

$ jq . /root/.ollama/models/manifests/registry.ollama.ai/library/llama3.2-vision/test
{
  "schemaVersion": 2,
  "mediaType": "application/vnd.docker.distribution.manifest.v2+json",
  "config": {
    "mediaType": "application/vnd.docker.container.image.v1+json",
    "digest": "sha256:5228822c05702a896f2753e70679a2b0a7f465e0348b830d3702da3c572c2c6d",
    "size": 564
  },
  "layers": [
    {
      "mediaType": "application/vnd.ollama.image.projector",
      "digest": "sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429",
      "size": 8077970976,
      "from": "/root/.ollama/models/blobs/sha256-7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429"
    },
    {
      "mediaType": "application/vnd.ollama.image.template",
      "digest": "sha256:715415638c9c4c0cb2b78783da041b97bd1205f8b9f9494bd7e5a850cb443602",
      "size": 269
    },
    {
      "mediaType": "application/vnd.ollama.image.license",
      "digest": "sha256:d3ed60b917572dd5aa69bf5ff7825f2db00d65e73dc07a43fbc31c60eb31449e",
      "size": 6018
    },
    {
      "mediaType": "application/vnd.ollama.image.license",
      "digest": "sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d",
      "size": 7711
    },
    {
      "mediaType": "application/vnd.ollama.image.params",
      "digest": "sha256:fefc914e46e6024467471837a48a24251db2c6f3f58395943da7bf9dc6f70fb6",
      "size": 32
    }
  ]
}

This is the same problem as when importing gemma3 GGUF files as reported in #10036 and #10121.

Proposed fix in #10162.

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.6.6, 0.6.8, 0.7.0

Originally created by @rick-github on GitHub (May 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10719 ### What is the issue? ```console $ ollama show --modelfile llama3.2-vision:latest > Modelfile $ ollama create llama3.2-vision:test gathering model components copying file sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429 100% parsing GGUF using existing layer sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429 using existing layer sha256:715415638c9c4c0cb2b78783da041b97bd1205f8b9f9494bd7e5a850cb443602 using existing layer sha256:d3ed60b917572dd5aa69bf5ff7825f2db00d65e73dc07a43fbc31c60eb31449e using existing layer sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d using existing layer sha256:fefc914e46e6024467471837a48a24251db2c6f3f58395943da7bf9dc6f70fb6 writing manifest success $ ollama run llama3.2-vision:test pulling manifest Error: pull model manifest: file does not exist ``` The reason is that the GGUF file is detected as a projector rather than as a fused GGUF: ```console $ jq . /root/.ollama/models/manifests/registry.ollama.ai/library/llama3.2-vision/test { "schemaVersion": 2, "mediaType": "application/vnd.docker.distribution.manifest.v2+json", "config": { "mediaType": "application/vnd.docker.container.image.v1+json", "digest": "sha256:5228822c05702a896f2753e70679a2b0a7f465e0348b830d3702da3c572c2c6d", "size": 564 }, "layers": [ { "mediaType": "application/vnd.ollama.image.projector", "digest": "sha256:7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429", "size": 8077970976, "from": "/root/.ollama/models/blobs/sha256-7633fdffe14c0f7acc115402376be5bd6052220c348676c5133dc011b35e2429" }, { "mediaType": "application/vnd.ollama.image.template", "digest": "sha256:715415638c9c4c0cb2b78783da041b97bd1205f8b9f9494bd7e5a850cb443602", "size": 269 }, { "mediaType": "application/vnd.ollama.image.license", "digest": "sha256:d3ed60b917572dd5aa69bf5ff7825f2db00d65e73dc07a43fbc31c60eb31449e", "size": 6018 }, { "mediaType": "application/vnd.ollama.image.license", "digest": "sha256:fcc5a6bec9daf9b561a68827b67ab6088e1dba9d1fa2a50d7bbcc8384e0a265d", "size": 7711 }, { "mediaType": "application/vnd.ollama.image.params", "digest": "sha256:fefc914e46e6024467471837a48a24251db2c6f3f58395943da7bf9dc6f70fb6", "size": 32 } ] } ``` This is the same problem as when importing gemma3 GGUF files as reported in #10036 and #10121. Proposed fix in #10162. ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.6.6, 0.6.8, 0.7.0
GiteaMirror added the bug label 2026-04-29 03:46:38 -05:00
GiteaMirror commented 2026-04-29 03:46:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 15, 2025):

Related: #10519

<!-- gh-comment-id:2885155794 --> @rick-github commented on GitHub (May 15, 2025): Related: #10519
GiteaMirror commented 2026-04-29 03:46:44 -05:00
Author
Owner
Copy Link

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

Fixed by #10722

<!-- gh-comment-id:2899277032 --> @rick-github commented on GitHub (May 21, 2025): Fixed by #10722
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#53555
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?