magnitudedev/LFM2.5-2.6B-DSpark-GGUF
Quantization vs LiquidAI/LFM2.5-2.6B-DSpark-GGUF. magnitudedev/LFM2.5-2.6B-DSpark-GGUF is a GGUF quantization (Q8_0) of the same weights: 23 tensors match exactly and 38 within quantization error.
Tensors changed: other 0/4, Norms 0/22, MLP 0/15, Attention 0/20