LWDCLS/NightWing3_Virtuoso-10B-v0.2-GGUF-IQ-Imatrix

Same weights, converted vs Nitral-Archive/NightWing3_Virtuoso-10B-v0.2. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160

On the Hub · Downloads on Model Pulse