mradermacher/Minerva-MoE-3x3B-GGUF

Same weights, converted vs ludocomito/Minerva-MoE-3x3B. Same weights stored in another dtype (BF16 → F16/F32), plus 96 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, other 0/32, Attention 0/128

On the Hub · Downloads on Model Pulse