Video + multi-image + text understanding at 8B parameters. The best vision model for 8GB VRAM setups — handles 40-frame video clips, multi-image comparison, and document understanding in a single context window.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 8GB VRAM Recommended
The MiniCPM-V 2.6 model by OpenBMB is a 8B parameter architecture optimized for vision tasks. It requires approximately 5.5GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 131,072 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running MiniCPM-V 2.6 at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 8GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run minicpm-v:8b' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.