#deepseek-v4 Repositories
Discover 7 active open source GitHub repositories tagged with #deepseek-v4, accumulating 24,387 total stars (averaging 3,483 stars per project). Leading this topic is FlashML-org/FreeToken with 17,522 stars.
7 repositories total
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
Zero-GPU CPU inference for 30Bโ284B MoE models (Qwen3.8 176.5B cold-cache certified in 28.26/48.35 GiB Cgroup v2, DeepSeek-V4 284B, Nemotron-30B) + RouteCrack 2.0.
๐ Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Lightweight open-source AI agent hub | Lightweight, multi-user open-source AI agent with tenant isolation, native DeepSeek support, and integration with multiple IM platforms
Xolotl: run DeepSeek-V4.1-Flash, all 552B parameters, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (Thinking Machines, own engine + MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM, and NVMe (Xolotl Direct). OpenAI + Anthropic API.
Frequently Asked Questions
What is the most popular #deepseek-v4 repository on GitHub?
The top ranked open source #deepseek-v4 project on GitHub is FlashML-org/FreeToken with 17,522 stars. FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
Which programming languages are most used in #deepseek-v4 repositories?
Among the top ranked #deepseek-v4 projects on GitHub, the most common programming languages are Python, Zig, Swift, C++.
How is the #deepseek-v4 repository ranking calculated?
We track 7 active open source repositories tagged with #deepseek-v4 (500+ stars), totaling 24,387 stars with an average of 3,483 stars per repository. Rankings update daily from the GitHub API.