mradermacher/Puma-3B-GGUF
Quantization vs acrastt/Puma-3B. mradermacher/Puma-3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 53 tensors match exactly and 184 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104