eryk-mazus/polka-1.1b-chat-gguf
Quantization vs eryk-mazus/polka-1.1b-chat. eryk-mazus/polka-1.1b-chat-gguf is a GGUF quantization (F16) of the same weights: 200 tensors match exactly and 1 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, MLP 0/66, Attention 0/88