mradermacher/apollo-astralis-2-i1-GGUF
Quantization (fewer layers) vs vanta-research/apollo-astralis-2. mradermacher/apollo-astralis-2-i1-GGUF matches part of vanta-research/apollo-astralis-2 (309 of its 531 tensors; the rest of vanta-research/apollo-astralis-2 has no counterpart). On the shared part: mradermacher/apollo-astralis-2-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 69 tensors match exactly and 240 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136