The-freezer/GLM-5.3-Flash-DERISKED-GGUF

Quantization vs Blackfrost-AI/GLM-5.3-Flash-ABLITERATED-F.U-AnthraClaud-Edition-BF16. The-freezer/GLM-5.3-Flash-DERISKED-GGUF is a GGUF quantization (Q6_K) of the same weights: 228 tensors match exactly and 494 within quantization error.

Tensors changed: Attention 0/388, lm_head 0/1, Embeddings 0/1, Norms 0/151, MLP 0/181

On the Hub · Downloads on Model Pulse