# Can the Radeon RX 9070 XT run MiniCPM-OCR-Jev?

> Yes. The Radeon RX 9070 XT runs MiniCPM-OCR-Jev fully in VRAM at FP16 / BF16 (about 4.7 GB of 16 GB).

Radeon RX 9070 XT: 16 GB (16 GB usable), 640 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M | Small loss | 1.93 | fits | — |
| Q8_0 | Lossless | 2.74 | fits | — |
| F16 (pick) | Lossless | 4.72 | fits | — |

## Run it

F16 straight from Hugging Face (ollama):

```bash
ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:F16
```

Docker with ROCm (AMD) (ollama):

```bash
docker run -d --name ollama --device /dev/kfd --device /dev/dri \
  -v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:F16
```

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

```bash
llama-server -hf openbmb/MiniCPM-OCR-Jev-gguf:F16
```

Docker with ROCm (AMD) (llama.cpp):

```bash
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -hf openbmb/MiniCPM-OCR-Jev-gguf:F16 --host 0.0.0.0 --port 8080 -ngl 99
```

Download with the lms CLI (lmstudio):

```bash
lms get openbmb/MiniCPM-OCR-Jev-gguf@F16
```

Serve an OpenAI-compatible API (vllm):

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

Smaller AWQ build (vllm):

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

Docker Compose (AMD ROCm) (vllm):

```yaml
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve openbmb/MiniCPM-OCR-Jev --host 0.0.0.0 --port 8000
    ports:
      - "8000:8000"
    ipc: host
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    security_opt:
      - seccomp=unconfined
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve openbmb/MiniCPM-OCR-Jev --host 0.0.0.0 --port 30000
```


## OCR models that fit comfortably

- [baidu/Unlimited-OCR](https://selfhost.directory/models/baidu/unlimited-ocr/on/rx-9070-xt): F16 ≈7.96 GB
- [deepseek-ai/DeepSeek-OCR](https://selfhost.directory/models/deepseek-ai/deepseek-ocr/on/rx-9070-xt): F16 ≈7.96 GB
- [baidu/Unlimited-OCR-2](https://selfhost.directory/models/baidu/unlimited-ocr-2/on/rx-9070-xt): F16 ≈7.97 GB
- [zai-org/GLM-OCR](https://selfhost.directory/models/zai-org/glm-ocr/on/rx-9070-xt): F16 ≈3.46 GB
- [deepseek-ai/DeepSeek-OCR-2](https://selfhost.directory/models/deepseek-ai/deepseek-ocr-2/on/rx-9070-xt): F16 ≈8.08 GB
- [dots-studio/dots.ocr](https://selfhost.directory/models/dots-studio/dots.ocr/on/rx-9070-xt): F16 ≈7.29 GB

## Other GPUs that run it

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

---
Model: https://selfhost.directory/models/openbmb/minicpm-ocr-jev. GPU: https://selfhost.directory/models/gpus/rx-9070-xt. Source: https://selfhost.directory/models/openbmb/minicpm-ocr-jev/on/rx-9070-xt