GLM 5.3 Flash NVFP4 local-run repo assembled, tested up to 1M context (512K recommended)
HankYeomans · x · 2026-10-25
HankYeomans pulled the commands from the Hugging Face model card for the newest GLM 5.3 Flash NVFP4 local model and assembled a repo for people with enough GPU to run it. It includes a TensorFold section (reworked from a DGX PR in the TensorFold repo) that works but remains a work in progress. In testing the model supports up to 1M context, though 512K is recommended. Links to the HF model page and runnable repo included.
More from Infra
- DeepInfer cluster serves 155T tokens/day on ~2,400 GPUs — roughly OpenRouter's weekly volume — AccBalanced · 2026-10-25
- SGLang vs vLLM: the inference framework race has no weekends — AccBalanced · 2026-10-25
- CASPA summit: chip-to-chip interconnect eats 60-70% of package energy, AI chip design targets 9-month cycles — ai · 2026-10-25
- 8 mixed GPUs plus 256GB DDR4 vs DGX Spark: is this MoE inference rig viable? — Ambitious_Fold_2874 · 2026-10-25
- DeepMind paper: 5-second-per-layer quadratic simulations predict LLM training spikes — burny_tech · 2026-10-25
- Ontology-Driven Observability: Building an End-to-End Knowledge Graph at Netflix Scale — blaizedsouza · 2026-10-25