selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

openbmb logo

Can the RTX A4000 run MiniCPM-OCR-Jev?

MiniCPM-OCR-Jev·2.2B·RTX A4000·16 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The RTX A4000 runs MiniCPM-OCR-Jev fully in VRAM at FP16 / BF16 (about 4.7 GB of 16 GB).

best quant
FP16 / BF16
needs
4.7 GB
usable
16 GB

Estimates from the model's size.Try other contexts on the MiniCPM-OCR-Jev page →

Every quantisation of MiniCPM-OCR-Jev on the RTX A4000

QuantMemoryFit
Q4_K_M 1.9 GBfits
Q8_0 2.7 GBfits
FP16 / BF16 pick4.7 GBfits

Speed is a bandwidth-based estimate for generating text (448 GB/s); prompt processing and long contexts are slower.

Run MiniCPM-OCR-Jev on the RTX A4000

Using FP16 / BF16, the best fit for RTX A4000.

Ollama · F16 straight from Hugging Facedocs
ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:F16
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf openbmb/MiniCPM-OCR-Jev-gguf:F16

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

LM Studio · Download with the lms CLIdocs
lms get openbmb/MiniCPM-OCR-Jev-gguf@F16

Then load it from the LM Studio app or with `lms load`.

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve openbmb/MiniCPM-OCR-Jev
vLLM · Smaller AWQ builddocs
vllm serve openbmb/MiniCPM-OCR-Jev-AWQ
vLLM · Docker Compose (NVIDIA)docs
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: openbmb/MiniCPM-OCR-Jev
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

SGLang · Serve an OpenAI-compatible APIdocs
sglang serve openbmb/MiniCPM-OCR-Jev --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve openbmb/MiniCPM-OCR-Jev --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]

API on port 30000.

OCR models that fit the RTX A4000 comfortably

All that fit →
ModelParamsBest quantMemoryLicence
3.3BA1.1BFP16 / BF16≈8.0 GBFits in memoryCommercial OK
deepseek-ai logoDeepSeek-OCRdeepseek-ai
3.3BA1.1BFP16 / BF16≈8.0 GBFits in memoryCommercial OK
3.3BA1.1BFP16 / BF16≈8.0 GBFits in memoryCommercial OK
zai-org logoGLM-OCRzai-org
1.3BFP16 / BF16≈3.5 GBFits in memoryCommercial OK
deepseek-ai logoDeepSeek-OCR-2deepseek-ai
3.4BA1.2BFP16 / BF16≈8.1 GBFits in memoryCommercial OK
dots-studio logodots.ocrdots-studio
3BFP16 / BF16≈7.3 GBFits in memoryCommercial OK

Other GPUs that run MiniCPM-OCR-Jev

Frequently asked questions

Can the RTX A4000 run MiniCPM-OCR-Jev?
Yes. The RTX A4000 runs MiniCPM-OCR-Jev fully in VRAM at FP16 / BF16 (about 4.7 GB of 16 GB).
Which quantisation of MiniCPM-OCR-Jev should I use on the RTX A4000?
FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.

Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.