# MiniCPM-V 4.7 1B (slim)

> MiniCPM-V 4.7 1B is OpenBMB's small open-weight vision-language model, 1.55B parameters, that reads images and video on a phone or laptop, calls tools, and ships in BF16, 4-bit and GGUF builds under Apache 2.0.

- Full: https://www.anchorterminal.com/tools/minicpm-v-4-7-1b.md (~9,900 tokens) · this version ~1,730 tokens · JSON https://www.anchorterminal.com/tools/minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/tools/minicpm-v-4-7-1b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10 · pricing https://www.anchorterminal.com/tools/minicpm-v-4-7-1b#pricing · reviews https://www.anchorterminal.com/tools/minicpm-v-4-7-1b#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 61/100 · rank #68 of 135 open-weight models · #57 in Open-weight models · not agent-ready · confidence low**


Assessment: A vision-language cousin small enough for a phone, under plain Apache 2.0, that every runtime we count can load. The projector is bigger than the language model, so plan for about 2 GB. The card says nothing about limits or training data and doesn't show how a tool call comes back.

## Facts

- Kind: Open-weight model · vendor: OpenBMB · category: Open-weight models · legal entity: OpenBMB (named in the GitHub LICENSE's copyright line) · provenance 58/100
- Packages: huggingface `openbmb/MiniCPM-V-4.7-1B`, huggingface `openbmb/MiniCPM-V-4.7-1B-gguf`, huggingface `openbmb/MiniCPM-V-4.7-1B-AWQ`, huggingface `openbmb/MiniCPM-V-4.7-1B-GPTQ`, huggingface `openbmb/MiniCPM-V-4.7-1B-int4`, ollama `openbmb/minicpm-v4.7:1b`
- Auth: None · pricing: Free · x402: no · licence: Apache-2.0
- Benchmark probes: not run yet, so Performance is pending
- Surface graded: The open weights at huggingface.co/openbmb/MiniCPM-V-4.7-1B and OpenBMB's own GGUF, AWQ, GPTQ and int4 repositories, read from the model card, the files and their metadata, the chat template and the runtimes' own code on 10 November 2026. OpenBMB's GitHub README, cookbook and licence file were read that day for the 35B-A3B listing. Nothing was downloaded or run
- Model: 1,554,476,272 parameters in BF16 per the safetensors metadata, the minicpmv4_7 architecture (MiniCPMV4_7ForConditionalGeneration), a dense qwen3_5_text language model of 24 layers and a 27-layer vision encoder that compresses visual tokens early, at 4x or 16x. Single images, several images and video in, text out
- Files: One safetensors file in BF16 (3.1 GB), a chat_template.jinja and no Python files. No pickle files. Hugging Face lists a SHA-256 for both large files. No LICENSE file in the repository; the licence is in the card's metadata and in OpenBMB's GitHub repository
- Licence: Apache 2.0 in the card's metadata and as the LICENSE file of github.com/OpenBMB/MiniCPM-V. Neither the card nor the GitHub README adds a use policy for this model
- Runtimes: Model code in Transformers from 5.18.0 (still in 5.22.2), vLLM 0.33.0 and SGLang 0.5.23, a guide and the projector type in llama.cpp (b12242), and an openbmb/minicpm-v4.7:1b tag in OpenBMB's namespace on Ollama. LM Studio's catalogue has no entry. The card also names OpenVINO
- Context: 262,144 tokens native (max_position_embeddings in the text config, and model_max_length in the tokenizer config). The card doesn't state a context length
- Tools and reasoning: The card shows a tool-calling request through Transformers' OpenAI-compatible server, with tools declared in the OpenAI tools array. The template declares tools in `<tools>` and expects `<function=...>` blocks in `<tool_call>`, several per turn. The card doesn't show a call coming back or name a parser. Thinking is off by default since 19 October 2026 and switches with `enable_thinking`
- Hardware: 3.1 GB in BF16, 2.4 GB for the AWQ build, 1.9 GB for GPTQ and 1.6 GB for int4. OpenBMB's GGUF files run from 0.55 GB (IQ3_XS) to 2.0 GB (F16), with Q4_K_M at 0.67 GB and a vision projector of 0.9 or 1.1 GB beside them
- Training data: Not described. The card covers the architecture and the on-device techniques and thanks Qwen3.5, Qwen3.6 and SigLIP2, and names no datasets, sizes or knowledge cut-off

- Scores: Capability pending, Reach 95, Risk 55, Agent interface 70, Documentation and upkeep 48 · total over the 7 assessed categories
- Why:  · Reach, Memory 30, OpenBMB's own IQ4_XS GGUF is 0.64 GB, 1.54 GB with the 0.90 GB vision projector, and 1.54 GB × 1.2 = 1.9 GB, which fits 16 GB wit… · Risk, File safety 25, safetensors in the main repository and the AWQ, GPTQ and int4 builds, GGUF in the GGUF build, with no .bin, .pt, .pth or .py… · Agent interface, Chat template 20, chat_template.jinja in the repository, 7,249 characters. · Documentation and upkeep, Model card 8, Intended use (image, multi-image and video understanding on device), architecture (early visual-token compression inside the v…
- Sources: 21, open questions: 5, both in the full twin
- Capabilities: model.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/minicpm-v-4-7-1b.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: Discord https://discord.gg/3cGQn9b3YM; https://github.com/OpenBMB/MiniCPM-V/issues; https://huggingface.co/openbmb/MiniCPM-V-4.7-1B/discussions; more in the full twin

## Before you call it

1. Start it with `llama-server -hf openbmb/MiniCPM-V-4.7-1B-gguf:Q4_K_M --jinja`, or `ollama run openbmb/minicpm-v4.7:1b`
2. For image input in llama.cpp add `mmproj-model-f16.gguf`, or the smaller 4x projector
3. The GGUF files at the repository root have thinking off. Use the files in `thinking/` when you want the trace
4. Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
5. Check tool calls in your runtime first, since the card names no parser
6. Validate JSON output yourself, since structured output isn't documented

## Connect

```bash
ollama run openbmb/minicpm-v4.7:1b
# or, with llama.cpp and OpenBMB's own GGUF:
llama-server -hf openbmb/MiniCPM-V-4.7-1B-gguf:Q4_K_M --jinja
# or, with Transformers' server, as the card gives it:
pip install "transformers[serving]>=5.18.0"
transformers serve openbmb/MiniCPM-V-4.7-1B --port 8000 --host 0.0.0.0
```

```bash
curl http://localhost:11434/api/chat \
  -d '{"model": "openbmb/minicpm-v4.7:1b", "messages": [{"role": "user", "content": "Hello!"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Qwen3-Embedding-8B | BB | 75.4 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-8b.min.md |
| Gemma 4 31B IT | BB | 74.1 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-31b-it.min.md |
| Qwen3-Embedding-4B | BB | 73.6 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md |
| Gemma 4 12B IT | BB | 72.3 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-12b-it.min.md |
| Gemma 4 26B A4B IT | BB | 72.2 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)