cactus-compute/cactus

Distribute and run LLMs with a single file.

Find the local LLM that actually runs and performs best on your hardware. Ranked by real,

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU.

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model