NikolayKozloff/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-Q8_0-GGUF
Quantization vs AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts. NikolayKozloff/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-Q8_0-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 98 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1