GLM-5.3 320B (18B active) Flash
on 2× NVIDIA DGX Spark · vLLM · 260,000 ctx
Oct 4, 2026
Use cases
codingvision
Summary
User reports GLM-5.3 Flash at ~40 t/s decode and ~1500 t/s prefill on 2x DGX Sparks.
Setup is vLLM with NVFP4 weights and DFlash2 speculative decoding, tensor parallel across 2 cards, 260k context via Claude Code scaffold; decode figure quoted at 100k context.
User says the model feels between GLM 5.1 and 5.3 for coding, has good vision and 3D understanding, and calls it a "good enough" home setup.