Download KTransformers
Get the latest version of KTransformers for your platform
Latest Release
0.3.1
Released on 2026-01-15
What's new:
- Improved MoE offloading performance
- Added support for DeepSeek-R1-671B
- Fixed memory leak in long conversations
- Better error messages for CUDA initialization
Choose Your Platform
π§
Linux
Ubuntu 20.04+, CUDA 11.8+
pip install ktransformersAppImage bundles CUDA runtime β no system CUDA Toolkit required, only an NVIDIA driver
Windows
Windows 10/11, CUDA 11.8+
pip install ktransformersQuick Install
The easiest way to install KTransformers is via pip
pip install ktransformersFor detailed installation instructions including CUDA setup, see the installation guide.
System Requirements
Minimum
- Python 3.9+
- CUDA 11.8+ (for GPU acceleration)
- 16 GB RAM
- NVIDIA GPU with 8GB+ VRAM
Recommended (for large models)
- Python 3.10+
- CUDA 12.0+
- 256 GB+ RAM
- NVIDIA RTX 4090 or higher