MaralGPT/MaralGPT-Mythos-9B-2606-GGUF

Same weights, converted vs MaralGPT/MaralGPT-Mythos-9B-2606. Same weights stored in another dtype (BF16 → BF16/F32), plus 24 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

1 derivatives checked

• liodon-ai/MaralGPT-Mythos-9B-2606-GGUF-imatrix-GGUF: Quantization

On the Hub · Downloads on Model Pulse