Apple M5 Ultra cluster hits 4.8TB/s bandwidth, rivaling data center GPUs
awnihannun · x · 2026-08-26
Exo partnered with Apple to implement low-latency RDMA over Thunderbolt 5, enabling Mac clusters to run massive models like Kimi K3 and GLM-5.3 at API speeds. A cluster of 4 x M5 Ultra Mac Studios scales to 4.8TB/s aggregate memory bandwidth, a speed previously only achievable with data center GPUs. Apple Silicon's superior memory unit economics and power efficiency make the 'data center on every desk' vision possible.
More from Infra
- Software folks don't get chip making: AlphaChip is just the tip of the iceberg — saranormous · 2026-08-26
- Nvidia BlueField 4 CPU Architecture Enables Tenant Network Isolation — bookwormengr · 2026-08-26
- NVIDIA Vera Rubin NVL72 racks enter production with 100% automated assembly — nvidia · 2026-08-26
- Hardware Prices Won't Recover: Choosing LLM Inference Hardware — nemuro87 · 2026-08-26
- For the price of one DGX Spark, you can build 2x 3090s with 128GB RAM — QuixiAI · 2026-08-26
- Train a private SLM on iMessages locally with MLX — romainhuet · 2026-08-26