yairpatch

/

Qwen3-VL-30B-A3B-Thinking-GGUF

like 29

Follow

yair patch 15

Have you tried the new patch? you should redownload the model as i reupload it

https://huggingface.co/yairpatch/Qwen3-VL-30B-A3B-Instruct-GGUF/tree/main

Have you tried the new patch? you should redownload the model as i reupload it

https://huggingface.co/yairpatch/Qwen3-VL-30B-A3B-Instruct-GGUF/tree/main

I tried the patches and they are still broken yes, also the most recent models. Everything I downloaded I downloaded yesterday, both models and patches, and the most recent changes to either repo was 3 days ago from what I'm seeing.

Have you tried the new patch? you should redownload the model as i reupload it

https://huggingface.co/yairpatch/Qwen3-VL-30B-A3B-Instruct-GGUF/tree/main

I tried the patches and they are still broken yes, also the most recent models. Everything I downloaded I downloaded yesterday, both models and patches, and the most recent changes to either repo was 3 days ago from what I'm seeing.

is it better response ?

how to load this model?

@yairzar it might be worth updating the readme of the model explaining that this isn't supported in the main branch of llama.cpp and therefore isn't supported in LM Studio/Ollama.