mradermacher/Firefly-V2Q-NonThinking-GGUF

Same weights, converted vs Guilherme34/Firefly-V2Q-NonThinking-RP. Same weights stored in another dtype (BF16 → F16/F32), plus 24 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

On the Hub · Downloads on Model Pulse