DeepSeek OCR models
2 DeepSeek OCR models from DeepSeek on Hugging Face, from 3.3B to 3.4B parameters, published by DeepSeek in BF16, with a 8K-token context. The smallest official model, DeepSeek-OCR, needs about 7.5 GB of VRAM at its published precision; the cheapest live fit is RTX 3060 at $0.110/hr.
Part of the DeepSeek series
Pick a size
One row per official DeepSeek OCR size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| DeepSeek-OCR | 3.3B | 7.5 GB | 3.7 GB | 1.9 GB | RTX 3060 | $0.110/hr | 1.9 GB |
| DeepSeek-OCR-2 | 3.4B | 7.6 GB | 3.8 GB | 1.9 GB | RTX 3060 | $0.110/hr | 1.9 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| DeepSeek-OCR | 3.3B | BF16 | 7.5 GB | RTX 3060 | $0.110/hr |
| DeepSeek-OCR-2 | 3.4B | BF16 | 7.6 GB | RTX 3060 | $0.110/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from DeepSeek
- DeepSeek R1 (14 models)
- DeepSeek V3 (7 models)
- DeepSeek Coder (6 models)
- DeepSeek V2 (5 models)
- DeepSeek VL (3 models)
- DeepSeek MoE (2 models)
- DeepSeek V4 (3 models)
