Archive
Discover and discuss technology tools
Explore the Tiscuss archive by category or keyword, then jump into conversations around what matters most.
Search and filters
AI AudioAI DesignAI FrameworkAI InfrastructureAI MarketingAI NewsAI ProductivityAI SearchAI SecurityAI ToolsAI VideoAI Writing
Active: AI Infrastructure / query: MoE / page 1 of 1 / 2 total
Qwen3.6-35B-A3B: AI Model on 16 GB M1 Pro with SSD-streamed MoE
Leveraging Qwen3.6 35B A3B on 16 GB M1 Pro with SSD streaming Mixture of Experts (MoE) The Qwen3.6 35B A3B AI model, when paired with a 16 GB M1 Pro processor a…
Global · Developers · Jul 19, 2026
Phase Router: Capacity-Aware Routing for Mixture of Experts
Phase Router: Efficient Routing for Mixture of Experts The Mixture of Experts (MoE) architecture has revolutionized various AI tasks by enabling models to utili…
Global · Developers · Apr 30, 2026