Nativ adds GLM-5.3 support: 505 tok/s on M3 Ultra
lllucas · x · 2026-08-27
Nativ announces day 0 support for GLM-5.3-Flash. On an M3 Ultra (512GB), the 320B MoE model achieves up to 505 tok/s prefill and 32 tok/s decode at 4-bit MLX, with peak memory under 380GB. Nativ is an open-source, SwiftUI-based macOS client for local AI.
More from Infra
- MiniCPM-V 4.7 runs a 35B MoE multimodal model on phones with just 3GB memory — nevrekaraishwa2 · 2026-10-15
- Nvidia Is Now Worth More Than the Entire Indian Stock Market — theteknosaur · 2026-10-15
- NVIDIA joins EU's AI in Science Enablers, offering compute, training and cloud resources — nordicinst · 2026-10-15
- Open source's hardware trap: data centers crowd out consumer GPUs, local LLMs become a privilege — Dante_77A · 2026-10-15
- NVIDIA backs EU AI in Science push as 35 supercomputers to serve 3M researchers — NVIDIA Blog · 2026-10-15
- Jensen Huang: 2027 AI bottleneck is 35GW of power, revenue justifies the capex — BG2 Pod · 2026-10-15