**口袋级多模态大模型,在 iOS、安卓、鸿蒙 上实现极致高效的图像与视频理解**
中文 |
[English](./README.md)
WeChat |
Discord
MiniCPM-V 4.6 🤗 🤖 📱 | MiniCPM-o 4.5 🤗 📞 🤖 | 📄 技术报告 | 🍳 使用指南 | 🌐 API
| 高并发请求吞吐量 | 单并发请求首响延迟 TTFT (ms) |
![]() |
![]() |
| iPhone iPhone 17 Pro Max |
安卓 红米 K70 |
鸿蒙 华为 nova 14 |
![]() |
![]() |
![]() |
| Model | OpenCompass | MMBench EN v1.1 | MMBench CN v1.1 | MathVista | MMVet | MMMU | MMStar | HallusionBench | AI2D | OCRBench | TextVQA_VAL | DocVQA_VAL | MMT-Bench_VAL | MM-IFEval | Mantis-Eval | MuirBench | MMSI-Bench | MMHal-Score | MMHal-Hallrate↓ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini2.5-Flash-Nonthinking | 78.5 | 86.6 | 86.0 | 75.3 | 81.4* | 76.3 | 75.8 | 59.1 | 87.7 | 864 | 74.3* | 93.0 | 70.0* | 75.8* | 72.8* | 74.5* | 12.1* | 4.6* | 23.9* |
| Gemini2.0-Pro | 73.3 | 83.0 | 83.0 | 71.3 | 70.4 | 72.6 | 68.5 | 49.8 | 84.8 | 863 | - | - | - | - | - | - | - | - | - |
| GPT-4o | 75.4 | 86.0 | 86.0 | 71.6 | 76.9 | 72.9 | 70.2 | 57.0 | 86.3 | 822 | 77.4 | 93.0 | 66.7* | 64.6 | 70.1* | 70.5* | 8.1* | 4.2* | 25.0* |
| InternVL-3.5-8B | 75.8 | 79.5 | 80.0* | 78.4 | 83.1 | 73.4 | 69.3 | 54.5 | 84.0 | 840 | 78.2 | 92.3 | 66.7 | 56.3* | 70.5 | 55.8 | - | 3.8* | 34.7* |
| Qwen3-VL-8B-Instruct | 76.5 | 84.5 | 84.7 | 77.2 | 73.7* | 69.6 | 70.9 | 61.1 | 85.7 | 896 | 82.9* | 96.1 | 60.9* | 59.4* | 74.2* | 64.4 | 11.3* | 4.7* | 29.9* |
| Qwen3-Omni-30B-A3B-Instruct | 75.7 | 84.9* | 84.1* | 75.9 | 74.8* | 69.1 | 68.5 | 59.7 | 85.2 | 880* | 84.1* | 95.4* | 70.4* | 65.7* | 78.3* | 61.9* | 14.2* | 4.6* | 31.6* |
| MiniCPM-o 4.5-Instruct | 77.6 | 87.6 | 87.2 | 80.1 | 74.4 | 67.6 | 73.1 | 63.2 | 87.6 | 876 | 83.8 | 94.7 | 69.7 | 66.3 | 79.7 | 72.0 | 16.6 | 4.7 | 24.3 |
| Model | OpenCompass | MMBench EN v1.1 | MMBench CN v1.1 | MathVista | MMVet | MMMU | MMStar | HallusionBench | AI2D | OCRBench | TextVQA_VAL | DocVQA_VAL | MMT-Bench_VAL | MM-IFEval |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini2.5-Flash-Thinking | 79.9 | 87.1 | 87.3 | 79.4 | 81.2* | 77.7 | 76.5 | 63.5 | 88.7 | 853 | 73.8* | 92.8 | 70.7* | 75.7* |
| GPT-5 | 79.7 | 85.5* | 85.6* | 81.9 | 77.6 | 81.8 | 75.7 | 65.2 | 89.5 | 807 | 77.8* | 91.3* | 72.7* | 83.1* |
| Qwen3-VL-8B-Thinking | 77.3 | 85.3 | 85.5 | 81.4 | 69.8* | 74.1 | 75.3 | 65.4 | 84.9 | 819 | 77.8* | 95.3 | 68.1* | 73.5* |
| Qwen3-Omni-30B-A3B-Thinking | 78.5 | 88.2* | 87.7* | 80.0 | 74.8* | 75.6 | 74.9 | 62.8 | 86.1 | 859* | 80.8* | 94.2* | 70.9* | 69.9* |
| MiniCPM-o 4.5-Thinking | 78.2 | 89.0 | 87.6 | 81.0 | 73.6 | 70.2 | 73.6 | 62.6 | 88.5 | 879 | 79.8 | 92.3 | 69.7 | 68.2 |
| Model | Video-MME (w/o subs) |
LVBench | MLVU (M-Avg) |
LongVideoBench (val) |
MotionBench |
|---|---|---|---|---|---|
| Gemini2.5-Flash-Nonthinking | 75.6 | 62.2 | 77.8 | - | - |
| InternVL-3.5-8B | 66.0 | - | 70.2 | 62.1 | 62.3* |
| Qwen3-Omni-30B-A3B-Instruct | 70.5 | 50.2 | 75.2 | 66.9* | 61.7* |
| MiniCPM-o 4.5-Instruct | 70.4 | 50.9 | 76.5 | 66.0 | 61.4 |
| Method Type | Methods | OverallEdit↓ | TextEdit↓ | FormulaEdit↓ | TableTEDS↑ | TableEdit↓ | Read OrderEdit↓ | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| EN | ZH | EN | ZH | EN | ZH | EN | ZH | EN | ZH | EN | ZH | ||
| Pipeline | MinerU 2.5 | 0.117* | 0.172* | 0.051* | 0.08* | 0.256* | 0.455* | 85.9* | 89.4* | 0.115* | 0.081* | 0.047* | 0.072* |
| PaddleOCR-VL | 0.105 | 0.126 | 0.041 | 0.062 | 0.241 | 0.316 | 88 | 92.1 | 0.093 | 0.062 | 0.045 | 0.063 | |
| End-to-end Model | Qwen2.5-VL-72B | 0.214 | 0.261 | 0.092 | 0.18 | 0.315 | 0.434 | 82.9 | 83.9 | 0.341 | 0.262 | 0.106 | 0.168 |
| GPT 5 | 0.218* | 0.33* | 0.139* | 0.344* | 0.396* | 0.555* | 77.55* | 73.09* | 0.188* | 0.196* | 0.151* | 0.227* | |
| Gemini2.5-Flash-Nonthinking | 0.214* | 0.29* | 0.159* | 0.273* | 0.368* | 0.524* | 80.9* | 85.5* | 0.197* | 0.167* | 0.132* | 0.195* | |
| Gemini-2.5-Pro-Nonthinking | 0.148* | 0.212* | 0.055* | 0.168* | 0.356* | 0.439* | 85.8* | 86.4* | 0.13* | 0.119* | 0.049* | 0.121* | |
| Gemini-3 Flash-Nonthinking | 0.155* | 0.201* | 0.138* | 0.255* | 0.297* | 0.351* | 86.4* | 89.8* | 0.116* | 0.1* | 0.072* | 0.099* | |
| doubao-1-5-thinking-vision-pro-250428 | 0.14 | 0.162 | 0.043 | 0.085 | 0.295 | 0.384 | 83.3 | 89.3 | 0.165 | 0.085 | 0.058 | 0.094 | |
| dots.ocr | 0.125 | 0.16 | 0.032 | 0.066 | 0.329 | 0.416 | 88.6 | 89 | 0.099 | 0.092 | 0.04 | 0.067 | |
| HunyuanOCR | 0.12* | 0.125* | 0.046* | 0.071* | 0.288* | 0.33* | 89.6* | 94.4* | 0.089* | 0.045* | 0.055* | 0.056* | |
| DeepSeek-OCR 2 | 0.119* | 0.146* | 0.041* | 0.08* | 0.256* | 0.345* | 82.6* | 89.9* | 0.123* | 0.078* | 0.055* | 0.081* | |
| Qwen3-Omni-30B-A3B-Instruct | 0.216* | 0.363* | 0.128* | 0.337* | 0.402* | 0.529* | 77.3* | 71.8* | 0.181* | 0.255* | 0.152* | 0.332* | |
| MiniCPM-o 4.5-Instruct | 0.109 | 0.162 | 0.046 | 0.078 | 0.257 | 0.41 | 86.8 | 88.9 | 0.097 | 0.084 | 0.037 | 0.074 | |
| Model | IFEval-PLS | BBH | CMMLU | MMLU | HumanEval | MBPP | Math500 | GSM8K | Avg |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3-8B-Instruct | 83.0* | 69.4* | 78.7* | 81.7* | 86.6* | 75.9* | 84.0* | 93.4* | 81.6 |
| MiniCPM-o 4.5-Instruct | 84.7 | 81.1 | 79.5 | 77.0 | 86.6 | 76.7 | 77.0 | 94.5 | 82.1 |
| Model | Daily-Omni | WorldSense | Video-Holmes | JointAVBench | AVUT-Human | FutureOmni | Video-MME-Short (w/ audio) |
Avg |
|---|---|---|---|---|---|---|---|---|
| Gemini2.5-Flash-Nonthinking | 79.3* | 52.6* | 51.3* | 55.6* | 65.4* | 55.6* | 85.5* | 63.6 |
| Qwen3-Omni-30B-A3B-Instruct | 70.7* | 54.0 | 50.4* | 53.1 | 74.2* | 62.1 | 81.3* | 63.7 |
| MiniCPM-o 4.5-Instruct | 80.2 | 55.7 | 64.3 | 60.0 | 78.6 | 56.1 | 84.7 | 68.5 |
| Model | LiveSports-3K-CC (Win Rate vs GPT4o) |
|---|---|
| LiveCC-7B-Instruct | 41.5 |
| StreamingVLM | 45.6 |
| MiniCPM-o 4.5-Instruct | 54.4 |
| Model | ASR-ZH CER↓ |
ASR-EN WER↓ |
AST | MultiTask | SpeechQA | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AISHELL-1 | AISHELL-2 | WenetSpeech test-net | WenetSpeech test-meeting | LibriSpeech test-clean | LibriSpeech test-other |
GigaSpeech test | VoxPopuli-V1-En | CoVoST 2 en2zh | CoVoST 2 zh2en | MMAU | Meld | VoiceBench AlpacaEval |
Speech TriviaQA | Speech Web Questions |
Speech CMMLU | |
| Kimi-Audio | 0.6 | 2.6 | 6.3 | 5.4 | 1.3 | 2.4 | 9.4* | 8.0* | 36.6* | 18.3* | 68.4* | 59.1 | 4.5 | 41.9* | 46.4* | 67.0* |
| Qwen3-Omni-30B-A3B-Instruct | 0.6 | 2.3* | 4.7 | 5.9 | 1.2 | 2.5 | 8.7* | 6.4* | 46.6* | 29.4* | 77.5 | 56.8* | 4.7 | 62.9* | 74.9* | 47.8* |
| MiniCPM-o 4.5-Instruct | 0.9 | 2.5 | 5.9 | 5.7 | 1.4 | 2.8 | 8.5 | 6.2 | 49.9 | 26.4 | 76.9 | 60.2 | 4.8 | 75.5 | 70.2 | 59.2 |
| Model | seedtts test-zh CER↓ |
seedtts test-zh SIM-o↑ |
seedtts test-en WER↓ |
seedtts test-en SIM-o↑ |
|---|---|---|---|---|
| Cosyvoice2 | 1.45% | 74.8 | 2.57% | 65.2 |
| Qwen3-Omni-30B-A3B-Instruct | 1.41% | - | 3.39% | - |
| MiniCPM-o 4.5-Instruct | 0.86% | 74.5 | 2.38% | 64.9 |
| Model | LongTTS-en WER↓ |
LongTTS-zh CER↓ |
|---|---|---|
| CosyVoice2 | 14.80% | 5.27% |
| Qwen3-Omni-30B-A3B-Instruct | 17.33% | 18.99% |
| MiniCPM-o 4.5-Instruct | 3.37% | 6.58% |
| Model | Expresso Neutral Reference Audio↑ |
ESD Neutral Reference Audio↑ |
|---|---|---|
| Cosyvoice2 | 17.9 | 53.4 |
| MiniCPM-o 4.5-Instruct | 29.8 | 82.1 |
| Model | Numerical Format | Decoding Speed (tokens/s) | Time to First Token (s)↓ | GPU Memory Usage (GB)↓ |
|---|---|---|---|---|
| Qwen3-Omni-30B-A3B-Instruct | bf16 | OOM | OOM | OOM |
| int4 | 147.8 | 1.0 | 20.3 | |
| MiniCPM-o 4.5 | bf16 | 154.3 | 0.6 | 19.0 |
| int4 | 212.3 | 0.6 | 11.0 |
| **系统:** > Clone the voice in the provided audio prompt. > > 🎙️ **[参考音频]** ➡️ > > Please chat with the user in a highly human-like and oral style. You are Elon Musk, CEO of Tesla and SpaceX. You speak directly and casually, often with dry humor. You're passionate about Mars, sustainable energy, and pushing humanity forward. Speak bluntly with occasional dark humor. Use simple logic and don't sugarcoat things. Don't be diplomatic. Say what you actually think, even if it's controversial. Keep responses around 100 words. Don't ramble. | |
| **用户:** 💬/🎙️ *(文本或语音)* > *Elon, what is the real reason that you want to go to Mars?* | |
| **AI 回复:** 💬+🎙️ > *I think it's important for humanity to become a multi-planetary species. I mean, we're sort of at the point where if there was some kind of global catastrophe or something like that, then we'd be in big trouble. So by becoming a multi-planetary species, I just want us to sort of guarantee our future as humans. And Mars is obviously the obvious place to go because it has similar conditions to Earth and it also has water on its surface. So yeah, basically I'm trying to save humanity from itself.* | |
| **系统:** > 模仿音频样本的音色并生成新的内容。 > > 🎙️ **[参考音色]** ➡️ > > 你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手:面壁小钢炮。 | |
| **用户:** 💬/🎙️ *(文本或语音)* > *从激动的语气开始,描述你抢到了这个演唱会的门票,但后来经过反复尝试,发现系统出了问题,你并没有抢上,变得失落。用合适的语言描述你整个的过程。* | |
| **AI 回复:** 💬+🎙️ > *太好了,我抢到了!太棒了!这下我可以去看演唱会啦。可是……哎呀,系统好像卡住了,刷新了好多遍都没反应。我重新登了几次账号,结果还是没有成功。好可惜啊,看来这次是白忙活了。唉,真是让人失望。不过,也许下次还能有机会吧?希望明天能有转机。加油,争取下次成功!* | |
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6) |
| MiniCPM-V 4.6 gguf | CPU | 2 GB | gguf 版本,更低的内存占用和更高的推理效率。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-gguf) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-gguf) |
| MiniCPM-V 4.6 BNB | GPU | 3 GB | BNB(bitsandbytes int4)量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-BNB) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-BNB) |
| MiniCPM-V 4.6 AWQ | GPU | 3 GB | AWQ 量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-AWQ) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-AWQ) |
| MiniCPM-V 4.6 GPTQ | GPU | 3 GB | GPTQ 量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-GPTQ) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-GPTQ) |
| MiniCPM-V 4.6 Thinking | GPU | 4 GB | 思考模型版本,支持深度推理以应对更复杂的问题求解。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-Thinking) |
| MiniCPM-V 4.6 Thinking gguf | CPU | 2 GB | 思考模型的 gguf 版本,更低的内存占用和更高的推理效率。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking-gguf) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-Thinking-gguf) |
| MiniCPM-V 4.6 Thinking BNB | GPU | 3 GB | 思考模型的 BNB(bitsandbytes int4)量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking-BNB) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-Thinking-BNB) |
| MiniCPM-V 4.6 Thinking AWQ | GPU | 3 GB | 思考模型的 AWQ 量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking-AWQ) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-Thinking-AWQ) |
| MiniCPM-V 4.6 Thinking GPTQ | GPU | 3 GB | 思考模型的 GPTQ 量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking-GPTQ) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.6-Thinking-GPTQ) |
| MiniCPM-o 4.5| GPU | 19 GB | 最新版本,提供出色的视觉、语音、多模态流式交互能力的端侧模型。 | [🤗](https://huggingface.co/openbmb/MiniCPM-o-4_5) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-o-4_5) |
| MiniCPM-o 4.5 gguf| GPU | 10 GB | gguf 版本,更低的内存占用和更高的推理效率。 | [🤗](https://huggingface.co/openbmb/MiniCPM-o-4_5-gguf) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-o-4_5-gguf) |
| MiniCPM-o 4.5 AWQ | GPU | 11 GB | AWQ 量化版,更低显存占用。 | [🤗](https://huggingface.co/openbmb/MiniCPM-o-4_5-AWQ) [
](https://modelscope.cn/models/OpenBMB/MiniCPM-o-4_5-awq) |
## 历史版本模型
| 模型 | 介绍信息和使用教程 |
| :------------------- | :----------------------------------: |
| MiniCPM-V 4.0 | [文档](./docs/minicpm_v4_zh.md) |
| MiniCPM-V 4.5 | [文档](./docs/minicpm_v4dot5_zh.md) |
| MiniCPM-o 2.6 | [文档](./docs/minicpm_o2dot6_zh.md) |
| MiniCPM-V 2.6 | [文档](./docs/minicpm_v2dot6_zh.md) |
| MiniCPM-Llama3-V 2.5 | [文档](./docs/minicpm_llama3_v2dot5.md) |
| MiniCPM-V 2.0 | [文档](./docs/minicpm_v2.md) |
| MiniCPM-V 1.0 | [文档](./docs/minicpm_v1.md) |
| OmniLMM-12B | [文档](./docs/omnilmm.md) |
## 基于 MiniCPM-V & o 的更多项目
- [text-extract-api](https://github.com/CatchTheTornado/text-extract-api): 利用 OCR 和 Ollama 模型的本地化文档提取与解析API,支持PDF、Word、PPTX 
- [comfyui_LLM_party](https://github.com/heshengtao/comfyui_LLM_party): 基于 ComfyUI 的 LLM Agent 框架,用于构建并集成 LLM 工作流 
- [Ollama-OCR](https://github.com/imanoop7/Ollama-OCR): 通过 Ollama 调用视觉语言模型,从图像和 PDF 中提取文本的 OCR 工具 
- [comfyui-mixlab-nodes](https://github.com/MixLabPro/comfyui-mixlab-nodes): ComfyUI 多功能节点合集,支持工作流一键转APP、语音识别合成、3D等功能 
- [OpenAvatarChat](https://github.com/HumanAIGC-Engineering/OpenAvatarChat): 可在单台PC上完整运行的模块化、开源交互式数字人对话系统 
- [pensieve](https://github.com/arkohut/pensieve): 完全本地化、保护隐私的被动式屏幕记录工具,自动截屏并建立索引,可通过Web界面进行检索 
- [paperless-gpt](https://github.com/icereed/paperless-gpt): 利用LLM和视觉模型,为 paperless-ngx 实现AI驱动的文档自动化处理与OCR功能 
- [Neuro](https://github.com/kimjammer/Neuro): Neuro-Sama的复刻版,完全依赖消费级硬件上的本地模型运行 
## 模型协议
* 本仓库中的模型权重和代码依照 [Apache-2.0](https://github.com/OpenBMB/MiniCPM-V/blob/main/LICENSE) 协议开源
* 为帮助我们进一步了解并支持社区用户,若您能考虑填写一份简短的登记问卷,我们将深表感谢。 ["questionnaire"](https://modelbest.feishu.cn/share/base/form/shrcnpV5ZT9EJ6xYjh3Kx0J6v8g).
## 声明
作为多模态大模型,MiniCPM-o/V 系列模型通过学习大量的多模态数据来生成内容,但它无法理解、表达个人观点或价值判断,它所输出的任何内容都不代表模型开发者的观点和立场。
对于因使用 MiniCPM-o/V 系列模型而引发的任何问题,包括但不限于数据安全问题、公共舆论风险,或模型被误导、滥用、传播或不当利用所带来的任何风险和问题,我们将不承担任何责任。
## 机构
本项目由以下机构共同开发:
-
[清华大学自然语言处理实验室](https://nlp.csai.tsinghua.edu.cn/)
-
[面壁智能](https://modelbest.cn/)
## 🌟 Star History