MiniCPM-V 4.6

OpenBMB · MiniCPM-V
MultimodalApache-2.0publicTrusted1.3B params

1.3B vision-language model: images and documents on small GPUs.

1.3B vision-language model: images and documents on small GPUs.

At a glance

  • Task: Multimodal (InferenceV1)
  • Params: 1.3B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 3 GB+ VRAM
  • dtype: Bf16, Fp16