Can the RTX A4000 run MiniCPM-OCR-1.0?
MiniCPM-OCR-1.0·1.3B·RTX A4000·16 GB VRAM
Yes. The RTX A4000 runs MiniCPM-OCR-1.0 fully in VRAM at FP16 / BF16 (about 2.2 GB of 16 GB).
- best quant
- FP16 / BF16
- needs
- 2.2 GB
- usable
- 16 GB
Estimates from the model's size.Try other contexts on the MiniCPM-OCR-1.0 page →
Every quantisation of MiniCPM-OCR-1.0 on the RTX A4000
| Quant | Memory | Fit |
|---|---|---|
| Q4_K_M | 1.1 GB | fits |
| Q8_0 | 1.4 GB | fits |
| FP16 / BF16 pick | 2.2 GB | fits |
Speed is a bandwidth-based estimate for generating text (448 GB/s); prompt processing and long contexts are slower.
Run MiniCPM-OCR-1.0 on the RTX A4000
Using FP16 / BF16, the best fit for RTX A4000.
ollama run hf.co/mradermacher/MiniCPM-OCR-1.0-GGUF:F16 llama-server -hf mradermacher/MiniCPM-OCR-1.0-GGUF:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get mradermacher/MiniCPM-OCR-1.0-GGUF@F16Then load it from the LM Studio app or with `lms load`.
vllm serve openbmb/MiniCPM-OCR-1.0 vllm serve openbmb/MiniCPM-OCR-1.0-AWQservices:
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]API on port 8000.
OCR models that fit the RTX A4000 comfortably
All that fit →| Model | Params | Best quant | Memory |
|---|---|---|---|
| 1.3B | FP16 / BF16 | ≈3.5 GBFits in memory | |
| 1.1B | FP16 / BF16 | ≈3.0 GBFits in memory | |
| 1.4B | FP16 / BF16 | ≈3.7 GBFits in memory | |
| 959M | FP16 / BF16 | ≈2.6 GBFits in memory | |
| 1B | FP16 / BF16 | ≈2.8 GBFits in memory | |
| 959M | FP16 / BF16 | ≈2.6 GBFits in memory |
Other GPUs that run MiniCPM-OCR-1.0
Frequently asked questions
- Can the RTX A4000 run MiniCPM-OCR-1.0?
- Yes. The RTX A4000 runs MiniCPM-OCR-1.0 fully in VRAM at FP16 / BF16 (about 2.2 GB of 16 GB).
- Which quantisation of MiniCPM-OCR-1.0 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.