NDIF is now available — free remote access to large-scale AI models for research.Get started →

Cracking open
AI's black box

The NSF National Deep Inference Fabric provides free remote access to large-scale AI models, enabling researchers and students to perform transparent, reproducible experiments on model internals.

Supported by

National Science Foundation
Northeastern University
NCSA
PIT-UN
0+
Research Institutions
0+
Research Citations
0+
GitHub Stars
0
H100 GPUs

What is NDIF?

The National Deep Inference Fabric is a unique nationwide research computing fabric that enables scientists to perform transparent and reproducible experiments on the largest-scale open AI systems. NDIF has three parts:

HPC Fabric

A nationwide high-performance computing fabric powered by NCSA's DeltaAI — 320 NVIDIA H100 GPUs delivering over 630 petaflops — providing free remote access to run experiments on large-scale AI models.

NNsight Library

An open-source PyTorch-based toolkit (850+ GitHub stars) that lets researchers inspect, modify, and customize AI model computations transparently — with a single remote=True flag.

Training Program

A nationwide training program developed with PIT-UN, a consortium of 63 universities and colleges, providing workshops, tutorials, and resources to build a broad community of AI researchers.

Remote Model Access

Access and inspect open-source model internals remotely through NDIF. Deploy models on-demand with full transparency into their computations.

All models are free for research use — no GPU required on your end.

Warm405B

Llama 3.1 405B

meta-llama/Meta-Llama-3.1-405B

Warm671B

DeepSeek R1

deepseek-ai/DeepSeek-R1

Hot70B

Llama 3.1 70B

meta-llama/Meta-Llama-3.1-70B

Hot8B

Llama 3.1 8B

meta-llama/Meta-Llama-3.1-8B

Featured Research

Researchers across 63+ institutions use NDIF and NNsight to uncover how large-scale AI models work, with 38+ published papers at top venues including ICLR, NeurIPS, ICML, and EMNLP.

Get Started in Minutes

Three simple steps to start running experiments on large-scale AI models.

01

Install NNsight

Install the open-source NNsight library with a single pip command.

$ pip install nnsight
02

Sign Up for Access

Create a free account to get remote access to large-scale models hosted on NDIF.

$ nnsight.net/signup
03

Start Experimenting

Run transparent, reproducible experiments on model internals — no GPU required.

$ model.trace(remote=True)

Join the NDIF Community

Be part of a growing network of researchers advancing AI transparency.

Join the Community

Connect with researchers, get help, and share your work on our Discord community.

Join Discord

Workshops & Events

Attend hands-on workshops and tutorials to learn how to use NDIF for your research.

See Events

Contribute

NNsight is open source. Contribute code, report issues, or improve the documentation.

View on GitHub