G
GLM-5.3-Flash (GGUF UD-Q4_K_XL + vision)
Z.ai (GGUF: unsloth) · GLM
LLMMITpublicTrusted321B params
llama.cpp GGUF build (UD-Q4_K_XL, Unsloth) of GLM-5.3-Flash, a 320B MoE with 18B active. The BF16 vision projector reads images.
GLM-5.3-Flash (GGUF UD-Q4_K_XL + vision)
Miner
The chat template of this build uses the 'break' tag. It needs a miner that renders every chat template as transformers does; the 0.0.10 release refuses this template on its text chat path.