NVIDIA App reserves 32GB of RAM by default on 64GB machines, hurting local AI
draginol · x · 2026-10-18
draginol found that after Windows first-launch setup, the NVIDIA App's System > Advanced settings default to reserving a huge chunk of system RAM as Dedicated GPU Memory — 32GB of his 64GB machine. This is a real problem for anyone running local AI, since unified memory gobbled by the GPU shrinks what's available for LLM inference.
The workaround: adjust the Dedicated GPU Memory slider in the NVIDIA App (the screenshot shows it set at the 48GB max, with an instability warning). He jokes reviewers won't notice since they get the 128GB model.
More from Infra
- China Rolls Out 'Token Factories' to Power Its AI Economy — nordicinst · 2026-10-18
- Running 20 concurrent low-latency regional-language voice agents on a single L4 GPU — DistrictUnique5259 · 2026-10-18
- AgentCave puts your scattered Macs and GPU boxes in one virtual room — noahsolomon · 2026-10-18
- Real AI demand estimated at ~$189B in 2026, over half from OpenAI and Anthropic — builderjaydub · 2026-10-18
- Twinax cable shipments in AI backplanes hit 85,200 km/year at 224G — moon-length in 4.5 years — jwt0625 · 2026-10-18
- DeepSeek-4.1-Flash Runs on 4x RTX Pro at 300+ TPS With NVMe Offload — TheZachMueller · 2026-10-18