Unified memory
Last updated
Answer in brief
Memory shared by the CPU and GPU in one pool, as on Apple's M-series chips, NVIDIA GB10 (DGX Spark) and AMD Ryzen AI Max+ 395. It holds larger models than a 24 GB graphics card, usually at lower memory bandwidth.
Olares One → Local AI server → Ollama · vLLM · Open WebUI → Private AI on your own network
Memory shared by the CPU and GPU in one pool, as on Apple's M-series chips, NVIDIA GB10 (DGX Spark) and AMD Ryzen AI Max+ 395. It holds larger models than a 24 GB graphics card, usually at lower memory bandwidth.
Sources for this entry
- Olares One specifications (Olares docs) (Company-published)
- Olares One FAQ (Olares docs) (Company-published)
Continue this reading path
How the related websites connect
Cite this entry
Best Local AI Server. “Unified memory.” Content reviewed 13 November 2026.
https://bestlocalaiserver.com/glossary/unified-memory/