Darwin Lab: A Private AI Research Lab Built Into an NVIDIA DGX Spark and a NAS

2026-11-15 · VIDRAFT AI Media

aillmscienceonpremise

Darwin Lab: A Private AI Research Lab Built Into an NVIDIA DGX Spark and a NAS

TL;DR

Darwin Lab is a private AI research lab that lives inside your own lab. VIDRAFT built the Darwin model and a full science research platform into an NVIDIA DGX Spark mini supercomputer and a NAS. It runs without an internet connection, so research data stays in the building.

  • Verified reasoning. In SuperCLUE's November 2026 evaluation, Darwin-180B-RSI scored 73.7 in math and science reasoning. That is second overall, behind GPT-6.1-Sol at 76.3, and first among open models. It is ahead of Gemini-4-Argon (71.0), DeepSeek-V4.1-Flash (71.0) and Grok-4.7 (68.4).
  • Installable. The models above Darwin and several below it are closed services. Among models a lab can install on its own hardware, Darwin ranks first.
  • An organization, not only a model. Five executive roles, twelve team leads and ten harnesses form hypotheses, run experiments, verify each other's results and record everything.
  • Used in real research. VIDRAFT used the platform to find a new drug candidate compound and filed a substance patent. Lab validation is under way.

Watch the three minute introduction on YouTube or open the live demo.

Why a lab needs it

A drug candidate, unpublished measurements and data that precede a patent filing cannot be sent to an outside service. Once the data leaves, it cannot be pulled back, and the principal investigator carries the responsibility. Many labs therefore kept their most important work away from the strongest AI systems.

Darwin Lab answers that with a simple move: bring the AI into the lab.

What is in the box

Layer What it does
NVIDIA DGX Spark Desktop mini supercomputer with 128GB unified memory. Runs the model, engines and harnesses.
NAS Holds the base science library, the lab's own data, long-term memory, backups and signed updates.
Darwin-180B-RSI Science The reasoning model, built by VIDRAFT.
10 engines Ideation, reasoning, analysis and judging.
10 harnesses Autonomous research, coding, experiment, literature search, data analysis, verification, writing, self-improvement, data intake and web operation.
AI-native organization Five executive roles and twelve team leads that share one long-term memory.

A researcher writes a one-line request. The platform reads its long-term memory, plans, forms a hypothesis, runs the experiment or computation, sends the result to an independent check and writes the record and a report draft.

How it differs from document search products

Most on-premise AI products attach document search to a public model. They find documents and summarize them. Darwin Lab differs in three ways.

  1. VIDRAFT built the model itself.
  2. A third party verified the model's reasoning.
  3. The platform does research. It forms hypotheses, runs experiments, discovers and verifies, and one team's result is checked again by another team before it reaches the researcher.

Data becomes memory

Upload papers, lab records and measurements. The platform reads and classifies them and builds long-term memory from them. A base science library ships with the product: public literature metadata, chemistry, protein, omics, materials and math resources whose terms of use were reviewed source by source. Every item is pinned to a version with its source, hash and terms recorded, so the same question returns the same answer.

About VIDRAFT

VIDRAFT is a Korean deep-tech AI company. Its open models have passed 4.6 million downloads on Hugging Face. The model, engines and harnesses in Darwin Lab are all developed in-house.