# Can the Tesla P40 run MiniCPM-OCR-1.0?

> Yes. The Tesla P40 runs MiniCPM-OCR-1.0 fully in VRAM at FP16 / BF16 (about 2.2 GB of 24 GB).

Tesla P40: 24 GB (24 GB usable), 347 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M | Small loss | 1.09 | fits | — |
| Q8_0 | Lossless | 1.41 | fits | — |
| F16 (pick) | Lossless | 2.19 | fits | — |

## Run it

F16 straight from Hugging Face (ollama):

```bash
ollama run hf.co/mradermacher/MiniCPM-OCR-1.0-GGUF:F16
```

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

```bash
llama-server -hf mradermacher/MiniCPM-OCR-1.0-GGUF:F16
```

Download with the lms CLI (lmstudio):

```bash
lms get mradermacher/MiniCPM-OCR-1.0-GGUF@F16
```

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve openbmb/MiniCPM-OCR-1.0
```

Smaller AWQ build (vllm):

```bash
vllm serve openbmb/MiniCPM-OCR-1.0-AWQ
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: openbmb/MiniCPM-OCR-1.0
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```


## OCR models that fit comfortably

- [zai-org/GLM-OCR](https://selfhost.directory/models/zai-org/glm-ocr/on/tesla-p40): F16 ≈3.46 GB
- [tencent/HunyuanOCR](https://selfhost.directory/models/tencent/hunyuanocr/on/tesla-p40): F16 ≈3 GB
- [XingChen-AGI/TeleOCR](https://selfhost.directory/models/xingchen-agi/teleocr/on/tesla-p40): F16 ≈3.66 GB
- [PaddlePaddle/PaddleOCR-VL-1.6](https://selfhost.directory/models/paddlepaddle/paddleocr-vl-1.6/on/tesla-p40): F16 ≈2.64 GB
- [lightonai/LightOnOCR-2-1B](https://selfhost.directory/models/lightonai/lightonocr-2-1b/on/tesla-p40): F16 ≈2.75 GB
- [PaddlePaddle/PaddleOCR-VL](https://selfhost.directory/models/paddlepaddle/paddleocr-vl/on/tesla-p40): F16 ≈2.64 GB

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rtx-4060): F16
- [Apple M4 (16 GB)](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/apple-m4-16gb): F16
- [Radeon RX 6700 XT](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rx-6700-xt): F16
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rtx-3060): F16
- [Arc B580](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/arc-b580): F16
- [Tesla T4](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/tesla-t4): F16
- [Arc A770 16GB](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/arc-a770): F16
- [Radeon RX 7800 XT](https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/rx-7800-xt): F16

---
Model: https://selfhost.directory/models/openbmb/minicpm-ocr-1.0. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/openbmb/minicpm-ocr-1.0/on/tesla-p40