deepseek-ai / image-text-to-text updated 10 months ago

DeepSeek-OCR

Name: DeepSeek-OCR
Author: deepseek-ai

🌟 Github 📥 Model Download 📄 Paper Link 📄 Arxiv Paper Link DeepSeek-OCR: Contexts Optical Compression Explore the boundaries of visual-text compression.

Params

3.3 B

Context

8,192

Downloads 30d

2.3 M

Likes

3,381

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days

▲ 17 K in the last 30 days (0.8%)

2.5 M2.1 M

Jul 28Aug 15Sep 2Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	6.7 GB	8.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: DeepseekOCRForCausalLM
Parameters: 3.3 B
Tensor type: BF16
Context length: 8,192
Vocabulary: 129,280
Layers / heads: 12 / 10
Licence: mit
First seen on the Hub: 2025-10-17
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any image-text-to-text model

Popular comparisons

Qwen3-VL-8B-Instruct 19.5 M Qwen3.5-9B 9.3 M Qwen3.5-4B 6.9 M Qwen3.5-2B 4.8 M Qwen3.8-27B-MLX-4bit 4.7 M Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF 4.0 M