mradermacher/Tankie-LFM2.5-1.2B-SFT-v1-i1-GGUF
Quantization vs WokeAI/Tankie-LFM2.5-1.2B-SFT-v1. mradermacher/Tankie-LFM2.5-1.2B-SFT-v1-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 45 tensors match exactly and 94 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24