Tagged with

3 articles found

768GB 10x GPU Mobile AI Rig: Redefining Local LLM and Generative AI Workstations

A custom-built, fully enclosed, portable 10-GPU AI workstation featuring dual high-core-count CPUs, 768GB RAM, and mixed 3090/5090 GPUs built for running large MoE models and high-detail generative tasks locally.

#distributed-inference#gpu-workstation#local-inference

kimi-k2

Trillion-Parameter AI on Your Desktop: The Kimi K2 Thinking Revolution Hits Local Hardware

Moonshot AI’s trillion-parameter reasoning model achieves unprecedented 30+ tokens/sec performance on consumer hardware through real-time GPU/CPU orchestration

#kimi-k2#local-inference#machine-learning...

ai-hardware

Desktop AI Wars: Is This $3K MiniPC Actually Bringing Cloud Performance Home?

Startup Olares bets $45M on cramming an RTX 5090 Mobile GPU into a 3.5L chassis – but can this ‘personal AI cloud’ deliver on its promises?

#ai-hardware#gpu-performance#local-inference...