mradermacher/SakaMoe-3x1.6B-Instruct-GGUF

Same weights, converted vs Sakalti/SakaMoe-3x1.6B-Instruct. Same weights stored in another dtype (F16 → F16/F32), plus 72 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/96, Attention 0/168

On the Hub · Downloads on Model Pulse