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

MiniCPM-OCR-Jev

openbmb·Instruct·released 23 Oct 2026

Apache 2.02.2B256K ctx ≈5.5 GB
Your GPU
ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:Q4_K_M
All 5 runners ↓

MiniCPM-OCR Jev (2B) is an OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct.

How much VRAM does MiniCPM-OCR-Jev need?

At FP16 / BF16 MiniCPM-OCR-Jev needs about 5.5 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use1.2 GB file≈1.9 GB
8-bitLossless in practice, twice the size of Q41.9 GB file≈2.7 GB
FP16 / BF16recommendedFull precision, as released3.5 GB file≈4.7 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

Can the RTX 4060 run MiniCPM-OCR-Jev? →

Run MiniCPM-OCR-Jev locally

--quantQ4_K_Mdefault; pick your GPU to tailor itopenbmb/MiniCPM-OCR-Jev-gguf

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf openbmb/MiniCPM-OCR-Jev-gguf:Q4_K_M

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

Install llama.cpp

Download with the lms CLIdocs
lms get openbmb/MiniCPM-OCR-Jev-gguf@Q4_K_M

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

Install LM Studio

Serve an OpenAI-compatible APIdocs
vllm serve openbmb/MiniCPM-OCR-Jev
Smaller AWQ builddocs
vllm serve openbmb/MiniCPM-OCR-Jev-AWQ
Docker Compose (NVIDIA)docs
yaml
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.

Install vLLM

Serve an OpenAI-compatible APIdocs
sglang serve openbmb/MiniCPM-OCR-Jev --host 0.0.0.0 --port 30000
Docker Compose (NVIDIA)docs
yaml
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.

Install SGLang

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
openbmb/MiniCPM-OCR-Jev-ggufGGUFIQ3_XS1.0 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFIQ3_M1.1 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFIQ4_XS1.2 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ4_01.2 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ4_K_S1.2 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFIQ4_NL1.2 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ4_K_M1.3 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ4_11.3 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ5_01.4 GB36.7K
openbmb/MiniCPM-OCR-Jev-ggufGGUFQ5_K_S1.4 GB36.7K

About MiniCPM-OCR-Jev

MiniCPM-OCR Jev (2B) is an OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct. MiniCPM-OCR Jev is a 2B OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct. Use it to auto-accept reliable regions, route the rest to human review, or pick the best result among several OCR models. • 🛡️ A small model that beats larger ones: at only 2B parameters, decision AUROC (×100) on • JevOCRBench is 93.6, above • JEV-35B-A3B (90.1) and close to Qwen3.5-397B-A17B (93.8). • 🧩 Stable generalization: on parses from MiniCPM-OCR 1.0, GLM-OCR, PaddleOCR-VL-1.6, and • Xiaomi-OCR-0, AUROC (×100) stays in 91.9–93.4. Trained from Qwen3.5-2B. The vision encoder and language backbone are retained, and the language-model output head lm_head is replaced with a binary classification head that learns whether a candidate is correct. When calling the cloud API, the Docker image, or the SDK service with a built-in renderer, supply the original region image, the candidate text, and the region category (text / formula / table) — the service renders internally. A service without a renderer requires you to supply the rendered image as well.

Full model card on Hugging Face →

Alternatives to MiniCPM-OCR-Jev

All alternatives →
baidu logo

Unlimited-OCR

baidu·OCR

≈4.5 GB

Please refer to the official vLLM recipe for deployment details:

3.3BA1.1B32K ctx MIT
5.6MJun 2026gguf
baidu logo

Unlimited-OCR-2

baidu·OCR

≈4.5 GB

Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention interactions from ultra-long sequences down to a fixed-size set of working references (e.g., 512 tokens).

3.3BA1.1B128K ctx MIT
621.8KOct 2026gguf
deepseek-ai logo

DeepSeek-OCR

deepseek-ai·OCR

≈4.5 GB

Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.

3.3BA1.1B8K ctx MIT
1.8MOct 2025ollama
zai-org logo

GLM-OCR

zai-org·OCR

≈3.5 GB

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization.

1.3B128K ctx MIT
2MJan 2026ollama
openbmb logo

MiniCPM-OCR-1.0

openbmb·OCR

≈3.4 GB

MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.

1.3B256K ctx Apache 2.0
280.7KOct 2026gguf
dots-studio logo

dots.mocr

dots-studio·OCR

≈4.1 GB

We present dots.mocr. Beyond achieving state-of-the-art (SOTA) performance in standard multilingual document parsing among models of comparable size, dots.mocr excels at converting structured graphics (e.g., charts, UI layouts, scientific figures and etc.) directly into SVG code.

3B128K ctx MIT
57.4KMar 2026gguf

MiniCPM-OCR-Jev FAQ

How much VRAM does MiniCPM-OCR-Jev need?
About 5.5 GB at FP16 / BF16.
Can MiniCPM-OCR-Jev run on the RTX 4060?
Yes. It fits at FP16 / BF16 (about 4.7 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use MiniCPM-OCR-Jev commercially?
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
How do I run MiniCPM-OCR-Jev with Ollama or llama.cpp?
With Ollama: ollama run hf.co/openbmb/MiniCPM-OCR-Jev-gguf:Q4_K_M. With llama.cpp: llama-server -hf openbmb/MiniCPM-OCR-Jev-gguf:Q4_K_M, which starts an OpenAI-compatible server.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.