King3Djbl/mythos-9b-merged
Quantization vs Qwen/Qwen3-8B. King3Djbl/mythos-9b-merged is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1
3 derivatives checked
- mradermacher/mythos-9b-merged-i1-GGUF: LoRA-style
- richardyoung/mythos-9b-unhinged-heretic: Quantization
- mradermacher/mythos-9b-merged-GGUF: Quantization