bartowski/GLM-5.3-Flash-BF16-GGUF

Quantization vs zai-org/GLM-5.3-Flash-BF16. bartowski/GLM-5.3-Flash-BF16-GGUF is a GGUF quantization (IQ1_M) of the same weights: 410 tensors match exactly and 312 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