CYGNUS Pro · v1.0.0-rc.7

Download CYGNUS

Native installers for macOS, Windows, and Linux. Five minutes from click to first response.

Auto-detected · 1.0.0-rc.7 Download for your platform
Detected: checking… · — · Not your platform? See all
All platforms

Pick your install

v1.0.0-rc.7 ships real Qwen-2.5-32B inference with the 25-probe Patent VII gauge-rotated adapter. Server-scored: the canonical classifier weights stay on the droplet — your machine holds only your R_device rotation and posts rotated readouts for canonical evaluation. A CUDA GPU with 24+ GB VRAM is required; first launch downloads the model (~20 GB) and installs the managed Python env.

macOS Coming soon
11 Big Sur or later · arm64 + x64
Notarized .dmg lands as soon as our Apple Developer ID certificate issues. Want first dibs? Email us and we'll ping you the day it ships.
Windows TBA
10 / 11 · 64-bit
Signed installer pending Sectigo EV certificate (5-7 business days from filing). Want a heads-up the day it's ready? Email us.
Linux
glibc 2.31+ · 64-bit · ~ 150 MB
.AppImage rc.7 .deb rc.1 — refresh pending
Release-candidate notice. v1.0.0-rc.7 ships unsigned while we finalize Apple Developer ID + Windows EV certificate procurement. (The .deb is still rc.1 — refresh pending; the .AppImage is the latest build.) On macOS: right-click the .dmg → Open → Open again to bypass Gatekeeper. On Windows: SmartScreen will warn — click More info → Run anyway. Always verify your download against the SHA-256 fingerprints below before installing. v1.0.0 (signed + notarized) ships ~ 2 weeks after rc feedback.

Linux: how to launch the .AppImage after download

AppImages are portable Linux binaries — no installer needed. After download you just need to mark the file executable.

Easy (file manager):

  1. Open Files / Nautilus and navigate to your Downloads folder.
  2. Right-click CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage → Properties → Permissions → tick Allow executing file as program.
  3. Double-click the file. CYGNUS launches.

Power-user (terminal):

cd ~/Downloads
chmod +x CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage
./CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage

First launch downloads the Qwen-2.5-32B model (~20 GB) and installs a managed Python environment under ~/.local/share/CYGNUS-Pro/. Allow 5–10 min on a fast connection. Activation token from your email is requested in the Onboarding wizard.

Verify your download (SHA-256)

Compute the SHA-256 of the file you downloaded and compare it byte-for-byte against the fingerprint below. If they match, the file is exactly what we built. If they don't — even by one character — discard it and redownload.

CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage
988c41501bc76bee25396963093c5d94cbb119a84c1129acea6b16bc56b6ae66
CYGNUS-Pro-1.0.0-rc.1-linux-amd64.deb
54931b08f7acf6847b1b776840df33be408b895c9d055c39d6b792f4da85aed0
How to verify on Linux / macOS: 
# run in the directory you saved the file to
sha256sum CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage
# expected:
988c41501bc76bee25396963093c5d94cbb119a84c1129acea6b16bc56b6ae66  CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage
How to verify on Windows (PowerShell): 
Get-FileHash .\CYGNUS-Pro-1.0.0-rc.7-linux-x86_64.AppImage -Algorithm SHA256
After install

Three steps to first response

i.

Launch & wait for the model

First boot loads Qwen-2.5-3B (~ 60 s on warm cache, ~ 90 s on cold). The status badge shows live progress. The 11 v6 probes finish loading next.

ii.

Activate (or stay in trial)

Settings → License → paste your activation key from the email we sent. Or skip — the trial gives you 7 days of full chat with the local probe-monitored model.

iii.

Send something to the model

Watch the 11 probes fire on the dashboard at ~ 10 Hz. Every response is QDKS-verdicted and recorded in the local audit log.

Requirements

System requirements

Mock mode (default)

  • 4 GB RAM
  • 2 GB free disk
  • No GPU required
  • Network only for license + auto-update checks
  • Internet for activation; offline thereafter for 7 days

Real-model mode (optional)

  • NVIDIA GPU with compute capability 7.0+ + ≥ 8 GB VRAM
  • CUDA 12.1+ runtime, recent driver
  • Python 3.10 with torch + transformers + bitsandbytes
  • ~ 6 GB free disk for the 4-bit Qwen-2.5-3B weights
  • v1.1 will install these for you in a managed venv