r0b0tlab/GLM-5.3-Flash-DFlash2-EXL3-3.00bpw
Same weights, converted vs incoai/GLM-5.3-Flash-DFlash2. Same weights stored in another dtype (BF16 → I16/F16), plus 144 new tensors.
Tensors changed: other 0/3, Norms 0/22, Attention 0/10, MLP 0/10
Same weights, converted vs incoai/GLM-5.3-Flash-DFlash2. Same weights stored in another dtype (BF16 → I16/F16), plus 144 new tensors.
Tensors changed: other 0/3, Norms 0/22, Attention 0/10, MLP 0/10