mradermacher/MiMo-NeoHorse-9B-AGSI-GGUF

Same weights, converted vs OliviaRossi/MiMo-NeoHorse-9B-AGSI. Same weights stored in another dtype (BF16 → F16/F32), plus 24 new tensors.

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

On the Hub · Downloads on Model Pulse