lmstudio-community/AFM-4.5B-GGUF

Quantization vs arcee-ai/AFM-4.5B. lmstudio-community/AFM-4.5B-GGUF is a GGUF quantization (Q8_0) of the same weights: 73 tensors match exactly and 218 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/72, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse