mradermacher/Cicikus-v3-1.4B-Opus4.6-Powered-GGUF

Same weights, converted vs pthinc/Cicikus-v3-1.4B-Opus4.6-Powered. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72

On the Hub · Downloads on Model Pulse