Hardware
What is VRAM (Video RAM)?
Dedicated memory on discrete GPUs used for model weights during inference. NVIDIA consumer GPUs have 8–24 GB VRAM, limiting the size of models they can run. Apple Silicon's Unified Memory effectively replaces VRAM by giving the GPU direct access to the full memory pool — a Mac with 128 GB can run models that would require multiple NVIDIA GPUs in a traditional setup.
Where VRAM (Video RAM) comes up on LLMCheck
- How to Fine-Tune a Local LLM on Mac with MLX (LoRA) — 2026 Guide
- How to Run Local LLMs on an Intel Mac (2026) — What's Possible & Realistic Speeds
- How to Run Llama 4 Locally on Mac — Scout & Maverick Guide
- Which Local LLM for Mac? The Ultimate Hardware & Specs Guide
- How Much RAM Do You Need to Run AI Locally on Mac?
- Apple Silicon Neural Engine Explained: How Your Mac Runs AI
See the best local LLMs for every Mac →