mradermacher/Rhea-72b-v0.5-i1-GGUF
Quantization vs davidkim205/Rhea-72b-v0.5. mradermacher/Rhea-72b-v0.5-i1-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 482 tensors match exactly and 561 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/640, lm_head 0/1