tensorblock/FluentlyLM-Prinum-GGUF
Quantization vs fluently/FluentlyQwen2.5-32B. tensorblock/FluentlyLM-Prinum-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448