Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-GGUF
Not comparable yet vs Nichonauta/LFM2.5-1.2B-Thinking-ToMoE. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (70 of 272/148 match), usually an architecture llama.cpp's name map doesn't cover yet.