Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Imported Chandra OCR 2 GGUF + mmproj fails for image inference on macOS MLX build (split vision / qwen35 compatibility) [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15203•Fetched 2026-04-08 02:25:17
View on GitHub
Comments
2
Participants
2
Timeline
3
Reactions
0
Author
kwoh80kwoh80
Participants
kwoh80kwoh80rick-githubrick-github
Timeline (top)
commented ×2closed ×1

I’m trying to import and run Chandra OCR 2 locally with Ollama on Apple Silicon macOS.

The model imports successfully, but image inference fails at runtime. This reproduces on:

  • Ollama 0.19.0
  • OLLAMA_NEW_ENGINE=true
  • current main built from source

Environment

  • macOS Apple Silicon
  • Metal / MLX path
  • Ollama 0.19.0
  • also reproduced on current main source build
  • model files:
    • chandra-ocr-2.Q8_0.gguf
    • chandra-ocr-2.mmproj-q8_0.gguf

Reproduction

  1. Import base model only:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf

  1. Import base + mmproj:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf FROM /tmp/chandra_gguf/chandra-ocr-2.mmproj-q8_0.gguf

  1. Create the model:

ollama create chandraq8mmproj -f Modelfile.mmproj

  1. Send an image generation request through /api/generate with an image + prompt.

Expected behavior

The imported Chandra multimodal model should accept image input and run OCR/reconstruction.

Actual behavior

Base-only import:

  • image inference fails with:
    • this model is missing data required for image input

Base + mmproj import:

  • api/tags shows the model and reports families like:
    • ["qwen35", "clip"]
  • but runtime inference fails with:
    • unable to load model

Relevant logs

model not yet supported by Ollama engine, switching to compatibility mode split vision models aren't supported llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'

API response: {"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Notes

This looks like the problem is not just missing mmproj data. The model appears to import and register correctly, but runtime loading fails for an imported split vision model using qwen35 + clip.

Questions

  • Is imported split-vision multimodal GGUF currently unsupported on Ollama for this architecture?
  • Is qwen35 multimodal import expected to work yet?
  • Is there a recommended import format or model packaging workaround for this kind of model?

Minimal log block:
```text
model not yet supported by Ollama engine, switching to compatibility mode
split vision models aren't supported
llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'
{"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Related references:

Error Message

llama_model_load: error loading model architecture: unknown model architecture: 'qwen35' {"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."} llama_model_load: error loading model architecture: unknown model architecture: 'qwen35' {"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Root Cause

I’m trying to import and run Chandra OCR 2 locally with Ollama on Apple Silicon macOS.

The model imports successfully, but image inference fails at runtime. This reproduces on:

  • Ollama 0.19.0
  • OLLAMA_NEW_ENGINE=true
  • current main built from source

Environment

  • macOS Apple Silicon
  • Metal / MLX path
  • Ollama 0.19.0
  • also reproduced on current main source build
  • model files:
    • chandra-ocr-2.Q8_0.gguf
    • chandra-ocr-2.mmproj-q8_0.gguf

Reproduction

  1. Import base model only:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf

  1. Import base + mmproj:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf FROM /tmp/chandra_gguf/chandra-ocr-2.mmproj-q8_0.gguf

  1. Create the model:

ollama create chandraq8mmproj -f Modelfile.mmproj

  1. Send an image generation request through /api/generate with an image + prompt.

Expected behavior

The imported Chandra multimodal model should accept image input and run OCR/reconstruction.

Actual behavior

Base-only import:

  • image inference fails with:
    • this model is missing data required for image input

Base + mmproj import:

  • api/tags shows the model and reports families like:
    • ["qwen35", "clip"]
  • but runtime inference fails with:
    • unable to load model

Relevant logs

model not yet supported by Ollama engine, switching to compatibility mode split vision models aren't supported llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'

API response: {"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Notes

This looks like the problem is not just missing mmproj data. The model appears to import and register correctly, but runtime loading fails for an imported split vision model using qwen35 + clip.

Questions

  • Is imported split-vision multimodal GGUF currently unsupported on Ollama for this architecture?
  • Is qwen35 multimodal import expected to work yet?
  • Is there a recommended import format or model packaging workaround for this kind of model?

Minimal log block:
```text
model not yet supported by Ollama engine, switching to compatibility mode
split vision models aren't supported
llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'
{"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Related references:

Fix Action

Fix / Workaround

  • Is imported split-vision multimodal GGUF currently unsupported on Ollama for this architecture?
  • Is qwen35 multimodal import expected to work yet?
  • Is there a recommended import format or model packaging workaround for this kind of model?

Code Example

Minimal log block:
RAW_BUFFERClick to expand / collapse

Summary

I’m trying to import and run Chandra OCR 2 locally with Ollama on Apple Silicon macOS.

The model imports successfully, but image inference fails at runtime. This reproduces on:

  • Ollama 0.19.0
  • OLLAMA_NEW_ENGINE=true
  • current main built from source

Environment

  • macOS Apple Silicon
  • Metal / MLX path
  • Ollama 0.19.0
  • also reproduced on current main source build
  • model files:
    • chandra-ocr-2.Q8_0.gguf
    • chandra-ocr-2.mmproj-q8_0.gguf

Reproduction

  1. Import base model only:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf

  1. Import base + mmproj:

FROM /tmp/chandra_gguf/chandra-ocr-2.Q8_0.gguf FROM /tmp/chandra_gguf/chandra-ocr-2.mmproj-q8_0.gguf

  1. Create the model:

ollama create chandraq8mmproj -f Modelfile.mmproj

  1. Send an image generation request through /api/generate with an image + prompt.

Expected behavior

The imported Chandra multimodal model should accept image input and run OCR/reconstruction.

Actual behavior

Base-only import:

  • image inference fails with:
    • this model is missing data required for image input

Base + mmproj import:

  • api/tags shows the model and reports families like:
    • ["qwen35", "clip"]
  • but runtime inference fails with:
    • unable to load model

Relevant logs

model not yet supported by Ollama engine, switching to compatibility mode split vision models aren't supported llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'

API response: {"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Notes

This looks like the problem is not just missing mmproj data. The model appears to import and register correctly, but runtime loading fails for an imported split vision model using qwen35 + clip.

Questions

  • Is imported split-vision multimodal GGUF currently unsupported on Ollama for this architecture?
  • Is qwen35 multimodal import expected to work yet?
  • Is there a recommended import format or model packaging workaround for this kind of model?

Minimal log block:
```text
model not yet supported by Ollama engine, switching to compatibility mode
split vision models aren't supported
llama_model_load: error loading model architecture: unknown model architecture: 'qwen35'
{"error":"unable to load model: /Users/.../.ollama/models/blobs/sha256-..."}

Related references:

extent analysis

TL;DR

The issue is likely due to Ollama's lack of support for split-vision multimodal models using the qwen35 architecture, and a workaround may involve waiting for an update or using a different model architecture.

Guidance

  • Verify that the issue is indeed related to the unsupported model architecture by checking the logs for the "unknown model architecture: 'qwen35'" error message.
  • Check the Ollama GitHub issues and releases for any updates or workarounds related to split-vision multimodal models, such as issues #9967, #11254, #9727, and #5245.
  • Consider using a different model architecture that is supported by Ollama, if possible.
  • Review the model import format and packaging to ensure it is correct and compatible with Ollama.

Example

No code snippet is provided as the issue is related to model compatibility and architecture.

Notes

The issue may be specific to the Apple Silicon macOS environment and the Ollama 0.19.0 version. The problem may be resolved in future updates or by using a different model architecture.

Recommendation

Apply workaround: Wait for an update or use a different model architecture, as the current qwen35 architecture is not supported by Ollama.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#prompt template#agent execution#callback error#memory management

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING