ggml-org/GLM-5.3-Flash-GGUF

Quantization vs zai-org/GLM-5.3-Flash-BF16. ggml-org/GLM-5.3-Flash-GGUF is a GGUF quantization (Q8_0) of the same weights: 15 tensors match exactly and 9 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/1, Norms 0/10, MLP 0/4, Attention 0/7

On the Hub · Downloads on Model Pulse