undreamai
Other architectures
Describe the bug
I've been experimenting with other models other than the ones that this asset lists out by default and have run into a huge number that can't be loaded because none of the available architectures can run it (including setting GPU cores to a value greater than 0).
Eg. https://huggingface.co/lmstudio-community/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/
I'm primarily doing this in an attempt to find a model that runs fast enough and is accurate enough for my needs.
Steps to reproduce
Add ("DeepSeek R1 Distill Qwen 1.5B", "https://huggingface.co/lmstudio-community/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf", null), to the model list, attempt to load it into the LLM.
LLMUnity version
2.5.2
Operating System
Windows
I'm actually getting this error on the Gemma 3 1B, Llama 3.2 1B, and Qwen 3 1.7B models that are in the original list, too.