GLM 5.3 open weights released with NVFP4 checkpoint achieving 4.4x throughput
songhan_mit · x · 2026-08-29
Zai has released the GLM 5.3 open-weight model. The IncoAI team, in collaboration, announced Day 0 support featuring several technical optimizations:
- DFlash 2 Drafter: Speculative decoding implementation.
- NVFP4 Checkpoint: Utilizing NVFP4 format for efficiency.
- Live Endpoint: Powered by TokenRouter's GB300s.
Benchmarks indicate up to 4.4× throughput improvement over native FP8 with autoregressive decoding.
Related event: Z.ai Open-Sources GLM-5.3 and GLM-5.3-Flash(28 posts)→
More from Infra
- Analyst: 80% of neoclouds may not survive, but the demand for their GPU capacity is real — BenBajarin · 2026-10-16
- Apple and Meta partner to run Muse Spark model on linked Mac Studios — pdamodaran · 2026-10-16
- Nvidia's developer base hits 11 million, up ~3.7x from 3 million in 2021 — Beth_Kindig · 2026-10-16
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Meta launches Muse Spark Open, says it runs on two M5 Ultra Mac Studios with Apple's help — The Verge AI · 2026-10-16