antirez/ds4
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
- 24kstars
- 2.4kforks
- 312open issues
- updated 3d ago
About ds4
ds4 is a free, open-source AI inference tool by antirez, written mainly in C. DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm. It has 24k GitHub stars and 2.4k forks, and was last updated 3d ago. It's released under the MIT license, a standard open-source license. According to the project, it works on macOS.
Similar free tools
cactus15k stars · Edge AI inference engine for mobile devices and wearables.
krasis526 stars · Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
llama.cpp134k stars · LLM inference in C/C++ with minimal setup and state-of-the-art performance.
llm-inference-engineering400 stars · Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.
inference9.6k stars · Serve and deploy AI models with a single command.
BitNet41k stars · Optimized inference framework for 1-bit LLMs on CPU and GPU.
ds4 FAQ
Can I use ds4 commercially?
Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is ds4 free?
Yes. ds4 is open source and free to use. It's released under the MIT license, a standard open-source license.
Does ds4 run on a Mac?
Yes. According to the project, ds4 works on macOS.
Does ds4 need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is ds4 still maintained?
Yes. It was last updated 3d ago and has 312 open issues on GitHub.
What are alternatives to ds4?
Similar free, open-source tools include cactus, krasis, llama.cpp, llm-inference-engineering.
