DevQuasar/zai-org.GLM-4.6V-Flash-GGUF

Quantization vs zai-org/GLM-4.6V-Flash. DevQuasar/zai-org.GLM-4.6V-Flash-GGUF is a GGUF quantization (Q8_0) of the same weights: 281 tensors match exactly and 242 within quantization error.

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