MiniCPM-V 4.7 35B-A3B (GGUF Q4_K_M + vision)

OpenBMB · MiniCPM-V
MultimodalApache-2.0publicTrusted35B params

OpenBMB's own llama.cpp GGUF build (Q4_K_M) of MiniCPM-V 4.7 35B-A3B: a MoE vision-language model with 3B active, 22 GB of weights.

OpenBMB's own llama.cpp GGUF build (Q4_K_M) of MiniCPM-V 4.7 35B-A3B: a MoE vision-language model with 3B active, 22 GB of weights.

At a glance

  • Task: Multimodal (InferenceV1)
  • Params: 35B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 25 GB+ VRAM
  • dtype: Int4