GLM-5.2
on NVIDIA DGX Spark · vLLM · 131,072 ctx
Sep 7, 2026
Use cases
long-contextcoding
Summary
User reports GLM-5.2 NVFP4 at about 15 t/s decode on short context and about 13 t/s at long context on a 4x DGX Spark setup, with about 512 t/s prefill.
Setup is 128K context with TP4/PP1/DCP4/MTP1 and an fp8 KV cache.