mradermacher/Aeonis-20b-GGUF

Quantization vs athirdpath/Aeonis-20b. mradermacher/Aeonis-20b-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 492 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/141, MLP 0/210, Attention 0/280, lm_head 0/1

On the Hub · Downloads on Model Pulse