mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF

Quantization vs open-machine/Llama-3.1-8B-FlashNorm-test. mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 65 tensors match exactly and 226 within quantization error.

Tensors changed: Norms 0/65, lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/128

On the Hub · Downloads on Model Pulse