LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF
Not comparable yet vs LiquidAI/LFM2.5-Audio-1.5B-JP. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (19 of 931/148 match), usually an architecture llama.cpp's name map doesn't cover yet.