sartajbhuvaji/GLM-4.6-Flash-text-GGUF

Same weights, converted vs sartajbhuvaji/GLM-4.6-Flash-text. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/80, Attention 0/280, lm_head 0/1

On the Hub · Downloads on Model Pulse