mradermacher/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1-GGUF

Same weights, converted vs Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1. Same weights stored in another dtype (BF16/F32 → F16/F32).

Tensors changed: Embeddings 0/2, Norms 0/76, other 0/44, MLP 0/90, Attention 0/32

On the Hub · Downloads on Model Pulse