DeepSeek OCR — Hardware Requirements & GPU Compatibility
Vision
DeepSeek OCR is a 3.3-billion-parameter vision-language model from DeepSeek, purpose-built for optical character recognition and document parsing rather than general chat. It pairs a vision encoder with a Mixture-of-Experts decoder that activates roughly 1.1 billion parameters per token, keeping decoding fast while all expert weights still need to fit in memory. Its core idea is compressing a page of text into a much smaller set of image tokens before decoding, and it is small enough to run on a single consumer GPU once quantized. Context length is limited to 8,192 tokens, reflecting its page-oriented use case. It is released under the MIT license, a highly permissive option for commercial use, and was published in October 2025, introducing "optical context compression" to shrink the token count needed for OCR.
2.2M downloads
3.4K likesSpecifications
- Publisher
- DeepSeek
- Family
- DeepSeek
- Parameters
- 3.3B
- Architecture
- DeepseekOCRForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2025-10-17
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does DeepSeek OCR Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.8 GB | 2.2 GB | 1.42 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 2.0 GB | 2.4 GB | 1.63 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 2.1 GB | 2.5 GB | 1.67 GB | 4-bit legacy quantization |
| Q4_K_Mest. | 4.80 | 2.4 GB | 2.8 GB | 2.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_0 | 5.00 | 2.5 GB | 2.9 GB | 2.09 GB | 5-bit legacy quantization |
| Q5_K_Mest. | 5.70 | 2.8 GB | 3.2 GB | 2.38 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 3.2 GB | 3.6 GB | 2.75 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.8 GB | 4.1 GB | 3.34 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 7.1 GB | 7.5 GB | 6.67 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run DeepSeek OCR?
Q4_K_M · 2.4 GBDeepSeek OCR (Q4_K_M) requires 2.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 8K context window can add up to 0.4 GB, bringing total usage to 2.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run DeepSeek OCR?
Q4_K_M · 2.4 GB59 devices with unified memory can run DeepSeek OCR, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download DeepSeek OCR
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does DeepSeek OCR need?
DeepSeek OCR requires 2.4 GB of VRAM at Q4_K_M, or 7.1 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3.3B × 4.8 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.8 GB (at full 8K context)
VRAM usage by quantization
Q4_K_M2.4 GBQ4_K_M + full context2.8 GB- What's the best quantization for DeepSeek OCR?
For DeepSeek OCR, Q4_K_M (2.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (2.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.8 GB.
VRAM requirement by quantization
Q2_K1.8 GBQ4_02.1 GBQ4_K_M ★2.4 GBQ5_02.5 GBQ6_K3.2 GBBF167.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run DeepSeek OCR on a Mac?
DeepSeek OCR requires at least 1.8 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run DeepSeek OCR locally?
Yes — DeepSeek OCR can run locally on consumer hardware. At Q4_K_M quantization it needs 2.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is DeepSeek OCR?
At Q4_K_M, DeepSeek OCR can reach ~389 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~519 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.4 × 0.65 = ~1220 tok/s
Estimated speed at Q4_K_M (2.4 GB)
~1220 tok/s~519 tok/s~1220 tok/s~1086 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of DeepSeek OCR?
At Q4_K_M, the download is about 2.00 GB. The full-precision BF16 version is 6.67 GB. The smallest option (Q2_K) is 1.42 GB.
- Which GPUs can run DeepSeek OCR?
52 consumer GPUs can run DeepSeek OCR at Q4_K_M (2.4 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run DeepSeek OCR?
59 devices with unified memory can run DeepSeek OCR at Q4_K_M (2.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.