# Can the RTX 4070 run Unlimited-OCR-2?

> Yes. The RTX 4070 runs Unlimited-OCR-2 fully in VRAM at FP16 / BF16 (about 7.1 GB of 12 GB).

GeForce RTX 4070: 12 GB (12 GB usable), 504 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M | Small loss | 2.77 | fits | — |
| Q8_0 | Lossless | 4 | fits | — |
| F16 (pick) | Lossless | 7.08 | fits | — |

## Run it

OpenAI-compatible server with a web UI (llama.cpp):

```bash
llama-server -hf AtomicChat/Unlimited-OCR-2-GGUF:BF16
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve baidu/Unlimited-OCR-2
```

Smaller FP8 build (vllm):

```bash
vllm serve AutomatosX/AX-Unlimited-OCR-2-AXQ-MXFP8
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: baidu/Unlimited-OCR-2
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve baidu/Unlimited-OCR-2 --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve baidu/Unlimited-OCR-2 --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Ask about an image (transformers):

```python
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="baidu/Unlimited-OCR-2", dtype="auto", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])
```


## OCR models that fit comfortably

- [baidu/Unlimited-OCR](https://selfhost.directory/models/baidu/unlimited-ocr/on/rtx-4070): F16 ≈7.96 GB
- [deepseek-ai/DeepSeek-OCR](https://selfhost.directory/models/deepseek-ai/deepseek-ocr/on/rtx-4070): F16 ≈7.96 GB
- [deepseek-ai/DeepSeek-OCR-2](https://selfhost.directory/models/deepseek-ai/deepseek-ocr-2/on/rtx-4070): F16 ≈8.08 GB
- [nanonets/Nanonets-OCR2-3B](https://selfhost.directory/models/nanonets/nanonets-ocr2-3b/on/rtx-4070): F16 ≈8.89 GB
- [dots-studio/dots.ocr](https://selfhost.directory/models/dots-studio/dots.ocr/on/rtx-4070): F16 ≈7.29 GB
- [nanonets/Nanonets-OCR-s](https://selfhost.directory/models/nanonets/nanonets-ocr-s/on/rtx-4070): F16 ≈8.89 GB

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rtx-4060): F16
- [Apple M4 (16 GB)](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/apple-m4-16gb): F16
- [Radeon RX 6700 XT](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rx-6700-xt): F16
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rtx-3060): F16
- [Arc B580](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/arc-b580): F16
- [Tesla T4](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/tesla-t4): F16
- [Arc A770 16GB](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/arc-a770): F16
- [Radeon RX 7800 XT](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rx-7800-xt): F16

---
Model: https://selfhost.directory/models/baidu/unlimited-ocr-2. GPU: https://selfhost.directory/models/gpus/rtx-4070. Source: https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rtx-4070