Z.ai

744B MoE (about 41B active) with DeepSeek sparse attention, AMD's MXFP4 release repacked byte for byte and served at 128K context with MTP on one 8-card Gaudi 2 node, through the glm-5-mxfp4 port.

1T-parameter MoE coding model (32B active, MLA, 384 experts) served text-only from AMD's MXFP4 release at 128K context on one 8-card Gaudi 2 node, through the kimi-k2-7 port, with the MXFP4 decode kernels behind one switch.

427B / 23B-active MoE served text-only on one 8-card Gaudi 2 node at 128K context, from AMD's MXFP4 checkpoint re-encoded exactly to per-channel FP8 experts.

816B MoE (42B active) with a latent MoE and per-expert output norm, the AMD Quark MXFP4 checkpoint as published, 256K tokens per request on one 8-card Gaudi 2 node, text only, through the muse-spark-open port.