How much RAM do I need to run an AI model locally?

It depends on the model's size. At Q4 quantization each parameter takes a little over half a byte, so the model alone needs a little over half its parameter count in gigabytes, plus memory for its context. The smallest model we track needs 1.4 GB, measured from its published files.

Do I need a graphics card to run open-source AI models?

No. Models run on ordinary system RAM using tools like Ollama or LM Studio, and Apple Silicon Macs are particularly good at it because they share memory between CPU and GPU. A dedicated graphics card is faster, but its VRAM is a hard ceiling: a 24GB card cannot run a model needing 30GB, even if the machine has 64GB of system RAM.

Are open-source AI models free to use?

The weights are free to download and run on your own hardware, so there is no per-token cost. Licences differ, though. Some permit commercial use freely, while others restrict it. Each model page lists its licence.

Open-source AI models

Open-source models are free to download and run on your own computer, with 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 60 language models we track, 35 run on a computer with up to 128GB of memory, from a laptop to a high-end workstation, plus 4 image generators.

What can your computer run?

Pick how much memory you have. It decides which models load.

System RAM

Graphics card

A hard ceiling: a model can't spill into system RAM.

With 16GB RAM, 17 of 60 models fit. Five of the most downloaded, smallest first:

Full list for 16GB RAM →

Memory is the Q4_K_M download size from Hugging Face plus the 4K-context cache and a runtime allowance. How this is calculated →

Browse by what it takes to run

Sorted by hardware, not by benchmark score.

Runs on a normal laptop

Fits in 16GB of RAM. No graphics card needed.

20 models

Runs on a good laptop or desktop

Wants 32GB of RAM, or a graphics card with 24GB of VRAM.

12 models

Needs a workstation

Wants 64–128GB. Realistically a high-end Mac or a multi-GPU build.

7 models

Too big for any home computer

Hundreds of gigabytes and a rack of GPUs. See exactly what they cost to run.

25 models

Jump to a memory size

8GB 16GB 24GB 32GB 64GB 128GB

Or a graphics card

8GB VRAM 12GB VRAM 16GB VRAM 24GB VRAM 32GB VRAM

Scale

How big do these things actually get?

Qwen3.8-2.4T-A95B has 2446B parameters and needs 2605 GB of memory at Q8_0, the smallest file published so far, about 36 H100 cards. Nobody runs it at a desk, but the numbers are worth seeing.

Most-downloaded of the models we track

HuggingFace downloads over the last 30 days, among the 64 current models listed here. Older models still in wide use (Qwen3, Llama 3, Qwen2.5) out-download all of these but fall outside the 12-month window.

1Qwen3.8-27BAlibaba / Qwen · 28B19 GBneeds 2GLM-5.3-FlashZhipu AI · 321B385 GBneeds, Q8_0 3MiniMax-H3MiniMax · 33B22 GBneeds 4Qwen3.8-Flash-NextAlibaba / Qwen · 180B · mixture-of-experts203 GBneeds, Q8_0 5GLM-5.3Zhipu AI · 753B820 GBneeds, Q8_0 6InklingThinking Machines Lab · 952B861 GBneeds, Q8_0 7Inkling-SmallThinking Machines Lab · 266B166 GBneeds 8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B · mixture-of-experts28 GBneeds 9MiniCPM5-2BOpenBMB · 2.5B2.3 GBneeds 10Laguna-S-2.1Poolside · 118B · mixture-of-experts100 GBneeds

New to running models yourself?

What does "quantized" mean?Why the same model comes in a dozen sizes.Why is a "small" model 40GB?Mixture-of-experts models are bigger than they look.Will it actually be fast?Having the RAM is not the same as having the speed.

Verified against HuggingFace on 2026-10-31Full model database (including paid APIs) →

Only models released in the last 120 days are listed, and an older generation drops off as soon as its successor ships. Specialised tools (OCR, speech recognition, translation, robotics and search embeddings) are left out. This list is general-purpose assistants, plus a few image generators.