nomic-ai/nomic-embed-text-v2-moe-GGUF

Same weights, converted vs nomic-ai/nomic-embed-text-v2-moe. Same weights stored in another dtype (F32 → F16/F32), plus 12 new tensors.

Tensors changed: other 0/2, Embeddings 0/1, Attention 0/48, MLP 0/30, Norms 0/48

On the Hub · Downloads on Model Pulse