mradermacher/Biggie-SmoLlm-0.4B-GGUF
Quantization vs nisten/Biggie-SmoLlm-0.4B. mradermacher/Biggie-SmoLlm-0.4B-GGUF is a GGUF quantization (F16) of the same weights: 73 tensors match exactly and 254 within quantization error.
Tensors changed: other 0/1, Attention 0/144, MLP 0/108, Norms 0/73, lm_head 0/1