Local AI Glossary
What is VRAM (Video RAM)?
Source: local-llm.net/glossary
Dedicated high-bandwidth memory on a GPU, used to store model weights, KV-cache, and intermediate computations during inference. Consumer GPUs offer 6-24 GB VRAM; professional GPUs offer 24-80 GB. VRAM capacity determines the largest model that can run entirely on the GPU.
How VRAM (Video RAM) fits in the local AI stack
VRAM (Video RAM) is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.
See also
- Full Local AI Glossary
- All learn topics
- What is Local AI?
- Quantization explained
- Hardware requirements
- How to choose a local LLM