Z.ai

106B MoE vision-language model (12B active) in FP8, 32K context on two Gaudi 2 cards.

744B MoE (about 41B active) with DeepSeek sparse attention, quantized to MXFP4 experts from the BF16 release and served at 128K context with MTP on one 8-card Gaudi 2 node, through the glm-5-mxfp4 port.

320B MoE (18B active) with KDA linear attention, NoPE MLA, mHC and image input, block FP8, 256K context on eight Gaudi 2 cards through the glm-5-3-flash port.