Koshkasa/Koshkasa_ArliAI_GLM-4.5-Air-Derestricted_REAP50_Creative-Q3_K_M

Quantization vs Koshkasa/ArliAI_GLM-4.5-Air-Derestricted_REAP50_Creative. Koshkasa/Koshkasa_ArliAI_GLM-4.5-Air-Derestricted_REAP50_Creative-Q3_K_M is a GGUF quantization (Q3_K_M) of the same weights: 276 tensors match exactly and 324 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/93, MLP 0/183, Attention 0/322, lm_head 0/1

On the Hub · Downloads on Model Pulse