MiniCPM-V 4.6
Collection
MLX variants of MiniCPM-V 4.6, 1.3B parameters (SigLIP2 400M vision encoder + Qwen3.5-0.8B LLM), repo: https://huggingface.co/openbmb/MiniCPM-V-4.6 • 7 items • Updated • 1
How to use from
PiConfigure the model in Pi
# Install Pi:
npm install -g @mariozechner/pi-coding-agent# Add to ~/.pi/agent/models.json:
{
"providers": {
"mlx-lm": {
"baseUrl": "http://localhost:8080/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "mlx-community/MiniCPM-V-4.6-nvfp4"
}
]
}
}
}Run Pi
# Start Pi in your project directory:
piQuick Links
mlx-community/MiniCPM-V-4.6-nvfp4
This model was converted to MLX format from openbmb/MiniCPM-V-4.6
using mlx-vlm version 0.4.5.
Refer to the original model card for more details on the model.
Use with mlx
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/MiniCPM-V-4.6-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
- Downloads last month
- 100
Model size
1B params
Tensor type
BF16
·
U8 ·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for mlx-community/MiniCPM-V-4.6-nvfp4
Base model
openbmb/MiniCPM-V-4.6
Start the MLX server
# Install MLX LM: uv tool install mlx-lm# Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/MiniCPM-V-4.6-nvfp4"