Tagged with

3 articles found

Apple’s M5 Ultra vs. $10K GPU Rig

The new M5 Ultra’s 1.2TB/s memory bandwidth is rewriting the rules for local AI inference. Here’s why the 3090 farm era might finally be over.

#LLM Inference#local AI#M5 Ultra...

AI Hardware

Xiaomi’s 1.22TB/s AI Cube Is a Brutal Assault on NVIDIA’s Local AI Empire

Xiaomi’s AI Cube prototype joins three custom chips to push 1.22TB/s memory bandwidth and run 120B local models. Here’s why it matters and what’s still missing.

#AI Hardware#chip design#Memory Bandwidth...

AI Inference

Apple M5 Max: 4x LLM Speed Is Nice, But 614GB/s Memory Bandwidth Is the Real Game Changer

Apple claims 4x faster LLM prompt processing on M5 Max compared to M4. We dig into the Fusion Architecture, unified memory bandwidth, and what 128GB of VRAM-equivalent actually means for running local AI.

#AI Inference#apple silicon#Local LLM...