warpfront/hipfire

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniM

Distribute and run LLMs with a single file.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.