#142 · Primary category： Inference & Local Deploy
ds4-control
macOS menubar app for fast local DeepSeek V4 Pro/Flash, with 1M context.
Project last updated：08/16/26
GitHub Stars
839
Forks
36
Contributors
2
License
MIT
Why we included this project
Running DeepSeek V4 on your own Mac usually means babysitting a server process, but this menu bar app takes over that job. It spawns the ds4-server child, waits for it to be ready, polls its health, and shuts it down cleanly, so you don't have to hand-roll launch scripts. The Pro/Flash picker checks whether a given variant and context length fit your machine's Metal memory limit and blocks configurations that would hang the system, which is a real relief when you're juggling 1M-token contexts. A built-in resumable downloader fetches the weights in parallel, and once the server is up you can launch Claude Code or Pi against it for agentic coding. For developers who want a private, always-available model on Apple Silicon, it turns a fiddly setup into something you can just leave running.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.