emwesoft/GLM-5.3-DFlash2-GGUF
Same weights, converted vs incoai/GLM-5.3-DFlash2. Same weights stored in another dtype (BF16 → BF16/F32), plus 28 new tensors.
Tensors changed: other 0/1, Norms 0/25, MLP 0/18, Attention 0/24
Same weights, converted vs incoai/GLM-5.3-DFlash2. Same weights stored in another dtype (BF16 → BF16/F32), plus 28 new tensors.
Tensors changed: other 0/1, Norms 0/25, MLP 0/18, Attention 0/24