redromnon/LFM2-700M-grammar-correction
Quantization vs LiquidAI/LFM2-700M. redromnon/LFM2-700M-grammar-correction is a GGUF quantization (Q8_0) of the same weights: 45 tensors match exactly and 93 within quantization error.
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24