v3.5 — Windows / macOS / Linux

Download BAVE

Free 7-day trial with full features. No credit card. Offline activation via machine config exchange.

Download Installer System Requirements
Download

BAVE-Setup-v3.5.0

NSIS installer (~2 GB). Bundles Python runtime, PyQt6, FFmpeg 8.1, AI models (BenForward_v5 + ViT-B/32), and all dependencies.

📦

BAVE-Setup-v3.5.0.exe

Version 3.5.0 • Windows 10/11 64-bit • ~2 GB

SHA256 Verified Code Signed NSIS LZMA
Download Now

Hosted on GitHub Releases. Checksums available on the release page.

Platforms

All Major Desktop Platforms

Windows

  • Windows 10/11 64-bit (1903+)
  • 4-core CPU minimum (i5-6400 / Ryzen 3 1200)
  • 8 GB RAM minimum, 16+ GB recommended
  • 10 GB free disk space (SSD recommended)
  • No GPU required
Download Windows

macOS

  • macOS 12+ (Monterey+)
  • Apple Silicon or Intel
  • 8 GB RAM minimum, 16+ GB recommended
  • 20 GB free disk space (SSD)
  • No GPU required
Download macOS

Linux (Beta)

  • Ubuntu 20.04+ / Fedora 35+ / Arch
  • x86_64 or ARM64
  • 8 GB RAM minimum, 16+ GB recommended
  • 20 GB free disk space (SSD)
  • No GPU required
Download Linux
Activation

Offline Activation Process

BAVE never requires internet. Activation is a one-time machine config exchange.

1️⃣

Generate Machine Config

On first launch, BAVE creates ~/.bave/machine_config.json with your hardware fingerprint (board/CPU/disk serials → SHA-256).

2️⃣

Submit to License Portal

Upload machine_config.json at bave.benyaminkhodabandeh.ir (or via email). Receive signed auth.dat.

3️⃣

Import & Encode

Drag auth.dat into BAVE. License verified offline via Ed25519 signature. No further network calls.

Bundle Contents

What's in the Installer

Core Runtime

  • Python 3.10+ (embedded)
  • PyQt6 6.11 (GUI framework)
  • FFmpeg 8.1 (x264, fdk-aac, libvmaf)
  • NSIS uninstaller

AI Models

  • BenForward_v5.pkl (feature cols, weights, candidates)
  • ben_forward_bitrate.onnx
  • ben_forward_vmaf.onnx
  • ben_forward_time.onnx
  • vit_b_32.pth (INT8 quantized)

Python Packages

  • torch 2.5.1+cpu
  • torchvision 0.20.1+cpu
  • onnxruntime 1.22.0
  • opencv-python 4.13.0
  • scenedetect 0.7
  • pandas 2.2.3, numpy 2.5.0
  • scikit-learn 1.9.0
  • cryptography 49.0.0