Download Latest Version textgen-portable-3.21-macos-arm64.zip (198.5 MB)
Email in envelope

Get an email when there's a new version of Text Generation Web UI

Home / v3.17
Name Modified Size InfoDownloads / Week
Parent folder
textgen-portable-3.17-windows-cuda12.4.zip 2025-11-06 907.6 MB
0
textgen-portable-3.17-windows-vulkan.zip 2025-11-06 211.8 MB
0
textgen-portable-3.17-windows-cpu.zip 2025-11-06 197.6 MB
0
textgen-portable-3.17-linux-cuda12.4.zip 2025-11-06 917.1 MB
0
textgen-portable-3.17-macos-x86_64.zip 2025-11-06 199.0 MB
0
textgen-portable-3.17-linux-vulkan.zip 2025-11-06 254.4 MB
0
textgen-portable-3.17-macos-arm64.zip 2025-11-06 183.1 MB
0
textgen-portable-3.17-linux-cpu.zip 2025-11-06 240.1 MB
0
README.md 2025-11-06 1.1 kB
0
v3.17 source code.tar.gz 2025-11-06 24.9 MB
0
v3.17 source code.zip 2025-11-06 25.0 MB
0
Totals: 11 Items   3.2 GB 0

Changes

  • Add weights_only=True to torch.load in Training_PRO for better security.

Bug fixes

  • Pin huggingface-hub to 0.36.0 to fix manual venv installs.
  • fix: Rename 'evaluation_strategy' to 'eval_strategy' in training. Thanks, @inyourface34456.

Backend updates

Portable builds

Below you can find self-contained packages that work with GGUF models (llama.cpp) and require no installation! Just download the right version for your system, unzip, and run.

Which version to download:

  • Windows/Linux:
  • NVIDIA GPU: Use cuda12.4.
  • AMD/Intel GPU: Use vulkan builds.

  • CPU only: Use cpu builds.

  • Mac:

  • Apple Silicon: Use macos-arm64.
  • Intel CPU: Use macos-x86_64.

Updating a portable install:

  1. Download and unzip the latest version.
  2. Replace the user_data folder with the one in your existing install. All your settings and models will be moved.
Source: README.md, updated 2025-11-06