QuantFactory/Ahma-3B-GGUF

Quantization vs Finnish-NLP/Ahma-3B. QuantFactory/Ahma-3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 53 tensors match exactly and 184 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104, lm_head 0/1

On the Hub · Downloads on Model Pulse