DuoNeural/LFM2.5-8B-A1B-TAP-DPQ-3.5bpw-GGUF
Quantization vs DuoNeural/LFM2.5-8B-A1B-Abliterated. DuoNeural/LFM2.5-8B-A1B-TAP-DPQ-3.5bpw-GGUF is a GGUF quantization (IQ3_S/Q3_K) of the same weights: 83 tensors match exactly and 67 within quantization error.
Tensors changed: Embeddings 0/2, other 0/36, MLP 0/28, Norms 0/60, Attention 0/24