---
title: MiniCPM-o-2_6-int4
canonical_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-o-2_6-int4"
md_url: "https://www.modelscope.cn/models/OpenBMB/MiniCPM-o-2_6-int4.md"
repository: OpenBMB/MiniCPM-o-2_6-int4
last_updated: 2026-08-24
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - minicpmo
architectures:
  - MiniCPMO
base_model:
  - openbmb/MiniCPM-o-2_6
base_model_relation: quantized
parameters: 8.7B
tensor_type:
  - BF16
  - I32
  - F32
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - Pytorch
language:
  - multilingual
downloads: 11202
stars: 18
tags:
  - minicpm-o
  - omni
  - vision
  - ocr
  - multi-image
  - video
  - custom_code
  - audio
  - speech
  - "voice cloning"
  - "live Streaming"
  - "realtime speech conversation"
  - asr
  - tts
---

# MiniCPM-o-2_6-int4

> MiniCPM-o-2_6-int4 - OpenBMB 在 ModelScope 开源的模型。A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

OpenBMB/MiniCPM-o-2_6-int4 是 ModelScope 魔搭社区上的 8.7B 参数any-to-any模型，采用 apache-2.0 许可，基于 openbmb/MiniCPM-o-2_6 构建。

- **Repository**: OpenBMB/MiniCPM-o-2_6-int4
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Parameters**: 8.7B
- **Base model**: openbmb/MiniCPM-o-2_6
- **Tags**: minicpm-o, omni, vision, ocr, multi-image, video, custom_code, audio, speech, voice cloning, live Streaming, realtime speech conversation, asr, tts
- **Downloads**: 11202
- **Stars**: 18
- **Last updated**: 2026-08-24

Source: https://www.modelscope.cn/models/OpenBMB/MiniCPM-o-2_6-int4

---

<h1>A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone</h1>

[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [MiniCPM Wiki(Chinese)](https://modelbest.feishu.cn/wiki/UtWxwcERfiRIpIkBOjuc3h9tn1D) | [Online Demo](https://minicpm-omni-webdemo-us.modelbest.cn) | [Technical Blog](https://openbmb.notion.site/MiniCPM-o-2-6-A-GPT-4o-Level-MLLM-for-Vision-Speech-and-Multimodal-Live-Streaming-on-Your-Phone-185ede1b7a558042b5d5e45e6b237da9) | [Join Us](https://mp.weixin.qq.com/mp/wappoc_appmsgcaptcha?poc_token=HAV8UWijqB3ImPSXecZHlOns7NRgpQw9y9EI2_fE&target_url=https%3A%2F%2Fmp.weixin.qq.com%2Fs%2FKIhH2nCURBXuFXAtYRpuXg%3F)


## MiniCPM-o 2.6 int4
This is the int4 quantized version of [**MiniCPM-o 2.6**](https://github.com/RanchiZhao/AutoGPTQ).   
Running with int4 version would use lower GPU memory (about 9GB).

### Prepare code and install AutoGPTQ

We are submitting PR to officially support minicpm-o 2.6 inference

```python
git clone https://github.com/RanchiZhao/AutoGPTQ.git && cd AutoGPTQ
git checkout minicpmo

# install AutoGPTQ
pip install -vvv --no-build-isolation -e .
```

### Usage of **MiniCPM-o-2_6-int4**

Change the model initialization part to `AutoGPTQForCausalLM.from_quantized`

```python
import torch
from transformers import AutoModel, AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

model = AutoGPTQForCausalLM.from_quantized(
    'openbmb/MiniCPM-o-2_6-int4',
    torch_dtype=torch.bfloat16,
    device="cuda:0",
    trust_remote_code=True,
    disable_exllama=True,
    disable_exllamav2=True
)
tokenizer = AutoTokenizer.from_pretrained(
    'openbmb/MiniCPM-o-2_6-int4',
    trust_remote_code=True
)

model.init_tts()

```

Usage reference [MiniCPM-o-2_6#usage](https://huggingface.co/openbmb/MiniCPM-o-2_6#usage)