320B Model Runs on Mac: OrcaSAQ Quantization Brings GLM-5.3 to Apple Silicon
alejandroll10 · x · 2026-08-27
OrcaRouter has natively brought the 320B-parameter GLM-5.3-Flash to Apple Silicon using a new method called OrcaSAQ (Orca Sensitivity-Aware Quantization). It supports 2/3/4/6-bit native MLX quantization without calibration and is architecture-aware. At 6-bit, it achieves 97.76% Top-1 agreement with FP8, delivering near-FP8 fidelity at a fraction of the memory.
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