LM Studio - Failed to load the model
#3
by
mknez78
- opened
I have tried to load Qwen__Qwen3-Next-80B-A3B-Instruct-MXFP4.gguf in LM Studio and get the error with msg:
🥲 Failed to load the model
Failed to load model
error loading model: error loading model architecture: unknown model architecture: 'qwen3next'
What could be the reason?
Because the llama.cpp code is still being worked on in the github PR Pull request: https://github.com/ggml-org/llama.cpp/pull/16095.
It may depends also on another PR https://github.com/ggml-org/llama.cpp/pull/16623
First it will need to be released before it gets picked up by lm-studio.
In the meantime you can use the PR 16095 as described in the product card in https://huggingface.co/lefromage/Qwen3-Next-80B-A3B-Instruct-GGUF/
or if you use Nvidia CUDA build from source from https://github.com/cturan/llama.cpp/releases/tag/test
Tnx for feedback!