magiccodingman/Seed-OSS-36B-Instruct-unsloth-MagicQuant-Hybrid-GGUF
Quantization vs unsloth/Seed-OSS-36B-Instruct. magiccodingman/Seed-OSS-36B-Instruct-unsloth-MagicQuant-Hybrid-GGUF is a GGUF quantization (Q8_0) of the same weights: 322 tensors match exactly and 449 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1