NikiKrutan/Kiwen1.2-27B-MTP-GGUF

Quantization vs beyoru/Kiwen1.2-27B. NikiKrutan/Kiwen1.2-27B-MTP-GGUF is a GGUF quantization (Q6_K) of the same weights: 161 tensors match exactly and 258 within quantization error.

Tensors changed: Norms 0/161, MLP 0/192, Attention 0/64, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse