Download Latest Version
textgen-portable-3.21-macos-arm64.zip (198.5 MB)
Get an email when there's a new version of Text Generation Web UI
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| textgen-portable-3.21-windows-cuda12.4.zip | 2025-12-15 | 939.9 MB | |
| textgen-portable-3.21-windows-cpu.zip | 2025-12-15 | 203.9 MB | |
| textgen-portable-3.21-windows-vulkan.zip | 2025-12-15 | 219.1 MB | |
| textgen-portable-3.21-linux-cuda12.4.zip | 2025-12-15 | 959.1 MB | |
| textgen-portable-3.21-linux-rocm.zip | 2025-12-15 | 379.8 MB | |
| textgen-portable-3.21-linux-vulkan.zip | 2025-12-15 | 271.4 MB | |
| textgen-portable-3.21-linux-cpu.zip | 2025-12-15 | 255.9 MB | |
| textgen-portable-3.21-macos-arm64.zip | 2025-12-15 | 198.5 MB | |
| README.md | 2025-12-15 | 1.0 kB | |
| v3.21 source code.tar.gz | 2025-12-15 | 24.9 MB | |
| v3.21 source code.zip | 2025-12-15 | 25.1 MB | |
| Totals: 11 Items | 3.5 GB | 16 | |
Changes
- Reduce the size of all Linux/macOS portable builds by excluding llama.cpp symlinks (dereferenced due to Python whl limitations) and recreating them on first launch.
Backend updates
- Update llama.cpp to https://github.com/ggml-org/llama.cpp/tree/5c8a717128cc98aa9e5b1c44652f5cf458fd426e
- Update ExLlamaV3 to 0.0.18
- Update safetensors to 0.7
- Update triton-windows to 3.5.1.post22
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
vulkanbuilds. -
CPU only: Use
cpubuilds. -
Mac:
- Apple Silicon: Use
macos-arm64.
Updating a portable install:
- Download and unzip the latest version.
- Replace the
user_datafolder with the one in your existing install. All your settings and models will be moved.
