GLM-5.3 320B (18B active) Flash

User runs a 186 GiB MoE model on 96 GB of VRAM, using host RAM for pinned experts, and reports 24.5 t/s decode at 8k context and 27.0 t/s at 0k. Prefill reaches 159 t/s at 27k. Host RAM is about 208 GB pinned, the CPU does no compute and only feeds experts, and transfers are NUMA-aware. The setup is NVIDIA SM120 only. Prefix caching with mid-prompt checkpoints cuts TTFT from 67.5s to 18.4s at 8k and from about 923s to 79s at 97k.