Open-source AI models

Open-source models are free to download and run on your own computer — no API key, no monthly fee, and nothing sent to anyone else's server. The catch is memory: a model has to fit in your RAM. Of the 28 language models we track, 19 run on ordinary consumer hardware, plus 2 image generators.

What can your computer run?

Two questions: how much memory you have, and what kind. The first decides what loads, the second decides how fast it runs.

1. How much memory?

System RAM
Graphics card (VRAM)
— a hard ceiling; a model can't spill into system RAM

2. What kind of machine?

On a Desktop or laptop — DDR5-5600 with 16GB RAM, 8 of 28 models fit. The most popular:

Full list for 16GB RAM

Memory figures are Q4_K_M at 4K context, including the context cache and runtime overhead. Speed is calculated, not measured: 90 GB/s × 0.65 ÷ bytes read per token.

Bandwidth source: 5,600 MT/s × 128-bit dual channel ÷ 8 = 89.6 GB/s. How these are worked out →

Browse by what it takes to run

Sorted by hardware, not by benchmark score.

Most-downloaded right now

What people are actually running this month, straight from HuggingFace.

New to running models yourself?

Verified against HuggingFace on 2026-08-01Full model database (including paid APIs) →
Only models released in the last 12 months are listed. Hardware pages: 8GB · 16GB · 32GB · 64GB · 128GB+ · 8GB · 12GB · 16GB · 24GB · 32GB