Eight DGX Spark nodes become one desk-side cluster: 1 TB of unified memory puts a 753B GLM 5.3 checkpoint on local hardware
NVIDIA announced at GTC Berlin official support for eight-node DGX Spark clusters, raising unified memory from 128 GB on a single node to 1 TB and letting frontier-class models that would not start on a four-node system load locally. The full GLM 5.3 (753B) checkpoint runs on the eight-node cluster, GLM 5.3 Flash generates at roughly 80 tokens per second, and decode throughput on dense Qwen3.8-27B (NVFP4) rises from about 12 TPS on one node to 52 TPS on eight.