Stars
4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script
Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)
The official Python library for the OpenAI API
Docker configuration for running VLLM on dual DGX Sparks
A free Linux distro with a Python-based userspace
RunCPM is a multi-platform, portable, Z80 CP/M 2.2 emulator.