xunkutech-ai/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp
Partial fine-tune vs empero-ai/Qwythos-9B-Claude-Mythos-5-1M. Partial change: 2% of the weights changed (mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 81/105, Attention 0/200, MLP 3/96
2 derivatives checked
- brainworkup/Qwythos-9B-v3-Claude-Mythos-5-1M-MLX-oQ8-mtp: Quantization
- xunkutech-ai/Qwythos-9B-Claude-Mythos-5-1M-MLX-oQ8-mtp: Quantization