Vision
How to deploy DeepSeek-OCR on a GPU cloud
A 3.3B (MoE) vision-language model that reads images alongside text. Full specs, license and use cases.
DeepSeek-OCR size and hardware requirements
3.3B
Total parameters
Mixture-of-experts: 6 of 64 experts active per token (exact active-parameter count not stated on the model card)
Active parameters
BF16
Published precision
7.5 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 6.2 GB | 7.5 GB | RTX 4070 Super | 1 | $0.110/hr |
| FP8 (quantized) | 3.1 GB | 3.7 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 1.6 GB | 1.9 GB | A16 | 1 | $0.059/hr |
How to run DeepSeek-OCR
Run DeepSeek-OCR with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve deepseek-ai/DeepSeek-OCR --tensor-parallel-size 1Run DeepSeek-OCR with Ollama
Verified against Ollama's own library listing.
ollama run deepseek-ocrDeploy DeepSeek-OCR on Aquanode
Aquanode has no one-click deploy template for DeepSeek-OCR; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× RTX 4070 Super or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod