Has anyone successfully loaded q8_0 gguf?

#7
by rthug - opened

I see 19k downloads, but I can't find any information about how to get around the qwen3vlmoe architecture error. If anyone has a solution it would be much appreciated!

What error message?

🥲 Failed to load the model

Failed to load model

error loading model: error loading model architecture: unknown model architecture: 'qwen3vlmoe'

^from LM-Studio, I get a similar error in ollama/llama.cpp

LMStudio can run the MLX version of Qwen3 VL, but it doesn't currently support the GGUF version. It seems LMStudio won't update its llama.cpp fork, and the official llama.cpp appears to have never supported Qwen3 VL.

Sign up or log in to comment