unsloth/GLM-4.5-Air-GGUF

Same weights, converted vs zai-org/GLM-4.5-Air. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 184 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/98, MLP 0/187, Attention 0/329, lm_head 0/1, other 0/2

1 derivatives checked

• rakmik/GLM-4.5-Air-GGUF_part10G: Quantization

On the Hub · Downloads on Model Pulse