Trillion-param models on a PC: hot weights in RAM, experts on NVMe
carrigmat · x · 2026-08-27
carrigmat explains why the weights don't all live in RAM:
- Most parameters in modern LLMs are experts activated only intermittently — those stay on NVMe drives.
- Only the persistently 'hot' weights remain in memory, so 128-192GB RAM plus NVMe can carry a trillion-parameter model.
Related event: $6,000 CPU-only server runs trillion-parameter open models locally(14 posts)→
More from Infra
- Next-gen GraalVM benchmarks: 4x faster startup, 2x less memory, no build step needed — RealGeneKim · 2026-10-15
- How Microsoft optimized Windows for Nvidia's Arm-based RTX Spark AI laptops — tomwarren · 2026-10-15
- How Microsoft optimized Windows for Nvidia's Arm-based RTX Spark laptops — The Verge AI · 2026-10-15
- Global smartphone shipments plunge 22% in worst quarterly decline on record as AI demand fuels memory costs — Polymarket · 2026-10-15
- SK Hynix drops 11% again, now below 3x FY2027 earnings as AI memory selloff deepens — JOBhakdi · 2026-10-15
- ASML Sells Zero Lithography Machines into Europe as US Hosts 75%+ of AI Compute — NinaDSchick · 2026-10-15