Choose a path

Cloud · Easiest

NVIDIA Brev Launchable

Provision a GPU instance, run the benchmark in a managed environment, download the evidence bundle. No local setup required.

Go to Launchable prep page →

Local · No GPU Required

Run Locally via GitHub

Clone the public repo. Python stdlib only, no dependencies to install. Runs the benchmark interface locally at localhost:7860.

Open GitHub repo →

Local reproduction

Run locally

Python stdlib only. No pip install required. The server starts immediately and serves the benchmark interface at localhost:7860. On Linux and Ubuntu, use python3; on Windows, use python.

Clone the public reproduction repo
git clone https://github.com/TeleMemetry/reproduce.git
cd reproduce
Start the benchmark server on Linux / Ubuntu
python3 demo_server.py
Windows alternative
python demo_server.py

Leave the terminal running. Then open your browser and paste http://127.0.0.1:7860 into the address bar. Do not run the URL as a terminal command.

Run the benchmark from the browser interface. When complete, download the evidence bundle from the results page.

Preflight

Confirm Python is available before running:

Linux / Ubuntu
python3 --version
Windows
python --version

Python 3.8 or later. No other dependencies. The server uses only the standard library.

What each run produces

Output from either path

NVIDIA Brev path

  • Per-probe scoring log
  • SHA256 receipt for the full run
  • Downloadable evidence bundle
  • Versioned bundle filename per run
  • GPU instance accessible for inspection

Local path

  • Per-probe scoring log
  • SHA256 receipt for the full run
  • Downloadable evidence bundle
  • Versioned bundle filename per run
  • Runs entirely on your machine

Claim boundary

What a public reproduction run proves

A public reproduction run proves that the probe-answer-score pipeline produces verified outputs against the public benchmark dataset, and that the resulting evidence bundle is SHA256-verifiable.

It does not prove production TeleMemetry internals. It does not claim to replace all databases, RAG, compression, or pruning in all systems. The benchmark demonstrates bit-perfect operational recall within the public benchmark scope.

Certified registry runs in the evidence library are produced by the private production harness and carry the full artifact chain required for engineering due diligence. Read the full IP boundary statement →