mradermacher

/

Qwen3-32B-i1-GGUF

like 1

Qwen 3 is a very new model so maybe it is not yet fully supported by 3rd party applications which might be using older version as llama.cpp in their backend. Try updating to the latest development version and if that doesn't work use llama.cpp instead. The error looks like LM Studio has some issues with the chat template. Likely similar to the one mentioned under https://github.com/ggml-org/llama.cpp/issues/13178 so maybe just use a different one or no chat template at all until this is fixed.