Lewdiculous/L3-8B-Stheno-v3.3-32K-GGUF-IQ-Imatrix
Same weights, converted vs Sao10K/L3-8B-Stheno-v3.3-32K. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
Same weights, converted vs Sao10K/L3-8B-Stheno-v3.3-32K. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1