LucianoM39/flushnet-local-llama-3.1-8b-q4km-layers
Quantization (fewer layers) vs meta-llama/Llama-3.1-8B-Instruct. LucianoM39/flushnet-local-llama-3.1-8b-q4km-layers matches part of meta-llama/Llama-3.1-8B-Instruct (9 of its 291 tensors; the rest of meta-llama/Llama-3.1-8B-Instruct has no counterpart). On the shared part: LucianoM39/flushnet-local-llama-3.1-8b-q4km-layers is a GGUF quantization (Q4_K/Q6_K) of the same weights: 2 tensors match exactly and 7 within quantization error.
Tensors changed: Norms 0/2, MLP 0/3, Attention 0/4