Tag
#local-inference
2 articles
Experiences with GLM-5.2 on the NVIDIA DGX Spark StackI split GLM-5.2, a 753B model, across two NVIDIA DGX Sparks to find the platform's ceiling.JUN 2026 · 13 MIN
Basic inference lab on the DGX Spark platformI built a multi-model inference rig on an NVIDIA DGX Spark, a data center shrunk to a desk.MAY 2026 · 18 MIN