OpenBMB/MiniCPM-V-4.7-1B-AWQ
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

This repository hosts the AWQ (W4A16, AutoAWQ) quantized version of MiniCPM-V 4.7 1B. For the original BF16 weights and the full model card, please refer to openbmb/MiniCPM-V-4.7-1B.

MiniCPM-V 4.7

Evaluation · Examples · Usage · Model weights

MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference. Notable features of MiniCPM-V 4.7 include:

  • 🔥 A New Pareto Frontier in Performance and Efficiency. As model capabilities continue to advance, inference efficiency has become an important measure of a model's value. On resource-constrained devices, delivering the strongest possible capabilities within a limited resource budget calls for higher capability density. The 1B variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier for MLLMs. In Instruct mode, the 1B variant continues to improve foundation capabilities over MiniCPM-V 4.6 and substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.
  • 🚀 Efficient Architecture. Based on the intra-ViT early compression technique from LLaVA-UHD v4, MiniCPM-V 4.7 compresses visual tokens early within the vision encoder, reducing computation in subsequent encoder layers. It also supports mixed 4x/16x visual token compression, allowing developers to balance visual detail and inference cost across tasks.
  • 💻 Broad Platform and Chip Support. MiniCPM-V 4.7 supports iOS, Android, and HarmonyOS, together with open-source on-device deployment support. It also provides day-0 support for chip platforms from Rockchip, Houmo, Intel, AMD, and Arm, extending deployment options across mobile and local computing devices.
  • 🛠️ Developer Friendly. MiniCPM-V 4.7 supports inference frameworks including SGLang, vLLM, llama.cpp, and Ollama, along with fine-tuning frameworks including SWIFT and LLaMA-Factory. It provides GGUF, BNB, AWQ, and GPTQ quantized variants and adds FP8 quantization support. We also release Self-Replay Fine-Tuning, a fine-tuning approach that helps developers extend model capabilities at low cost while reducing forgetting of existing capabilities, making further customization easier.

Get started

Model weights  ·  Inference  ·  Fine-tuning  ·  Live demo  ·  Local deployment  ·  API  ·  Cookbook

Evaluation

Significantly Advancing the Performance–Efficiency Pareto Frontier

The 1B variant of MiniCPM-V 4.7 advances the performance–efficiency Pareto frontier. In Instruct mode, 1B substantially outperforms Qwen3.5 0.8B in both overall score and inference efficiency.

Performance versus inference time for MiniCPM-V 4.7 1B

Overall Performance (1B, Instruct)

Full performance comparison for MiniCPM-V 4.7 1B in Instruct mode

Examples

MiniCPM-V 4.7 can run on phones and tablets. The clips below are unedited screen recordings captured directly on the devices.

1B
iPhone 17 Pro Max

Usages

Inference with Transformers

Click to expand the Transformers inference examples.
Installation
pip install "transformers[torch]>=5.18.0" torchvision torchcodec

Note on CUDA compatibility: torchcodec (used for video decoding) may have compatibility issues with certain CUDA versions. For example, torch>=2.11 bundles CUDA 13.1 by default, while environments with CUDA 12.x may encounter errors such as RuntimeError: Could not load libtorchcodec. Two workarounds:

  1. Replace torchcodec with PyAV — supports both image and video inference without CUDA version constraints:
    pip install "transformers[torch]>=5.18.0" torchvision av
  2. Pin the CUDA version when installing torch to match your environment (e.g. CUDA 12.8):
    pip install "transformers>=5.18.0" torchvision torchcodec --index-url https://download.pytorch.org/whl/cu128
Load the Model
import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "openbmb/MiniCPM-V-4.7-1B"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto"
)

# Flash Attention 2 is recommended for faster inference and lower GPU memory usage,
# especially in multi-image and video scenarios.
# model = AutoModelForImageTextToText.from_pretrained(
#     model_id,
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )
Image Inference
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/refract.png"},
            {"type": "text", "text": "What causes this phenomenon?"},
        ],
    }
]

downsample_mode = "16x"  # Using `downsample_mode="4x"` for Finer Detail

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt",
    downsample_mode=downsample_mode,
    max_slice_nums=36,
    enable_thinking=False,
).to(model.device)

generated_ids = model.generate(**inputs, downsample_mode=downsample_mode, max_new_tokens=512)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])
Video Inference
messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/football.mp4"},
            {"type": "text", "text": "Describe this video in detail. Follow the timeline and focus on on-screen text, interface changes, main actions, and scene changes."},
        ],
    }
]

downsample_mode = "16x"  # Using `downsample_mode="4x"` for Finer Detail

inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt",
    downsample_mode=downsample_mode,
    max_num_frames=128,
    stack_frames=1,
    max_slice_nums=1,
    use_image_id=False,
    enable_thinking=False,
).to(model.device)

generated_ids = model.generate(**inputs, downsample_mode=downsample_mode, max_new_tokens=2048)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])
Advanced Parameters

You can customize image/video processing by passing additional parameters to apply_chat_template:

ParameterDefaultApplies toDescription
downsample_mode"16x"Image & VideoVisual token downsampling. "16x" merges tokens for efficiency; "4x" keeps four times as many tokens for finer detail. Must also be passed to generate().
max_slice_nums9Image & VideoMaximum number of slices when splitting a high-resolution image. Higher values preserve more detail for large images. Recommended: 36 for image, 1 for video.
max_num_frames128Video onlyMaximum number of main frames sampled from the video.
stack_frames1Video onlyTotal sample points per second. 1 = main frame only (no stacking). N (N>1) = 1 main frame + N−1 sub-frames per second; the sub-frames are composited into a grid image and interleaved with main frames. Recommended: 3 or 5.
use_image_idTrueImage & VideoWhether to prepend <image_id>N</image_id> tags before each image/frame placeholder. Recommended: True for image, False for video.

Note: downsample_mode must be passed to both apply_chat_template (for correct placeholder count) and generate (for the vision encoder). All other parameters only need to be passed to apply_chat_template.

Serving with transformers serve

Hugging Face Transformers includes a lightweight OpenAI-compatible server for quick testing and moderate-load deployment.

pip install "transformers[serving]>=5.18.0"

Start the server:

transformers serve openbmb/MiniCPM-V-4.7-1B --port 8000 --host 0.0.0.0

Send a request:

curl -s http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "openbmb/MiniCPM-V-4.7-1B",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/openbmb/DemoCase/resolve/main/refract.png"}},
        {"type": "text", "text": "What causes this phenomenon?"}
      ]
    }]
  }'

Tool calling example:

curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{
  "model": "openbmb/MiniCPM-V-4.7-1B",
  "messages": [{"role": "user", "content": [
    {"type": "text", "text": "the weather of Beijing"}
  ]}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the current weather for a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "City name"}
        },
        "required": ["location"]
      }
    }
  }]
}'

Speculative decoding (DSpark)

Click to show speculative decoding.

Speculative decoding (DSpark): we also release MiniCPM-V-4.7-1B-DSpark, a DSpark draft model trained for MiniCPM-V-4.7-1B.

Inference with OpenVINO™

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference on Intel CPU/GPU/NPU platforms. OpenVINO provides day-0 support for MiniCPM-V-4.7 on Intel platforms with high-performance inference. See the OpenVINO™ Toolkit to get started. You can install and run the example with this notebook (link TBD).

On-Device Deployment

MiniCPM-V 4.7 supports deployment on iOS, Android, and HarmonyOS, with day-0 support for Rockchip, Houmo, Intel, AMD, and Arm chip platforms. See the edge deployment repository for the apps and source code.

Inference and Fine-Tuning

For supported inference and training frameworks, see Supported Inference and Training Frameworks and API. The MiniCPM-V 4.7 Cookbook covers deployment, fine-tuning, and quantization workflows.

Task guides

  • Single-image chat
  • Multi-image chat
  • Video understanding
  • OCR
  • PDF parsing
  • Visual grounding

Quantization

MethodGuide
GGUFQuantization guide
BNBQuantization guide
AWQQuantization guide
GPTQQuantization guide
FP8 / INT4Quantization guide

Acknowledgements

Click to view acknowledgements.

We would like to thank the following projects:

  • Qwen3.6 for providing the language backbone
  • SigLIP2 for providing the vision understanding module
  • Transformers

Model Weights

MiniCPM-V 4.7 is available in the following variants:

ModelDescriptionDownload
MiniCPM-V 4.7 1BCombines stronger capabilities with extremely high efficiency, advancing the performance–efficiency Pareto frontier for multimodal large language models.🤗   
MiniCPM-V 4.7 1B int4bitsandbytes int4 quantized version with lower GPU memory usage.🤗   
MiniCPM-V 4.7 1B AWQAWQ (W4A16) quantized version with lower GPU memory usage.🤗   
MiniCPM-V 4.7 1B GPTQGPTQ (W4A16) quantized version with lower GPU memory usage.🤗   
MiniCPM-V 4.7 1B GGUFGGUF version with lower memory usage for CPU inference.🤗   
MiniCPM-V 4.7 1B DSparkDSpark draft model for speculative decoding.🤗   

Also available on Ollama.