DeepSeek-OCR — DeepSeek 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
A 3B vision-language model built for one job — turning document pages into structured text — and a demonstration of "contexts optical compression": rendering text as an image and decoding it costs roughly 10x fewer tokens at near-lossless fidelity, or 20x at about 60% precision. A DeepEncoder compresses each page into vision tokens which a DeepSeek-3B MoE decoder reads, activating only ~570M parameters. A second generation, DeepSeek-OCR-2, followed in January 2026.
变体
DeepSeek-OCR 最小的变体在 Q4_K_M 下约需 3 GB 显存——量化权重加框架开销，不含 KV 缓存。
| 模型 | Q4 下显存 | 显存 | 上下文 | 运行 |
|---|---|---|---|---|
| DeepSeek-OCR 3B → 3B (0.57B active) | ~2.6 GB | 8,192 | ollama run deepseek-ocr |
显存为 Q4_K_M 下的量化权重加开销，与 GPU 与显存检测器使用同一引擎计算。
如何在本地运行 DeepSeek-OCR
安装 Ollama，然后拉取标签。
ollama run deepseek-ocr在上方选择一个尺寸，查看它自己的显存、速度估算和安装命令。
许可证
Commercial use permitted. No usage restrictions beyond attribution.
适用于: DeepSeek-OCR 3B推荐 GPU
目录中能在本地运行 DeepSeek-OCR（至少 3 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
我的 GPU 能运行 DeepSeek-OCR 吗？
DeepSeek-OCR — 常见问题
How much VRAM does DeepSeek-OCR need?
DeepSeek-OCR needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek-OCR 3B (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run DeepSeek-OCR on an RTX 4090 (24 GB)?
Yes — DeepSeek-OCR runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for DeepSeek-OCR?
Q4_K_M is the best balance of quality and VRAM for DeepSeek-OCR in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run DeepSeek-OCR with Ollama?
DeepSeek-OCR has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.