#146 · Primary category： Inference & Local Deploy
deepseek-ocr.rs
Rust multi‑backend OCR/VLM engine (DeepSeek‑OCR-1/2, PaddleOCR‑VL, DotsOCR) with DSQ quantization and an OpenAI‑compatible server & CLI – run locally without Python.
Project last updated：02/21/26
GitHub Stars
2.2K
Forks
169
Contributors
7
License
Apache-2.0
Why we included this project
Document-understanding models like DeepSeek-OCR normally want a Python runtime, but this Rust engine runs them natively on your own hardware. It wraps three OCR/VLM backends (DeepSeek-OCR, PaddleOCR-VL, and DotsOCR) behind one CLI and an OpenAI-compatible HTTP server, so you can batch documents from the terminal or plug it into tooling that already speaks the chat-completions API. Model weights download automatically from Hugging Face or ModelScope, and each model comes in DSQ-quantized variants (Q4_K, Q6_K, Q8_0) that keep memory low enough for a 16GB laptop or a CPU-only node. Acceleration targets Apple Metal, experimental CUDA, and Intel MKL, and the README is upfront about each backend's memory footprint so you can pick the right one. If you want a self-contained OCR service you can embed rather than a Python deployment, the native binaries and deterministic asset caching remove most of the setup friction.
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.