Instructions to use nativ-community/MiniCPM-V-4.7-1B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nativ-community/MiniCPM-V-4.7-1B-8bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("nativ-community/MiniCPM-V-4.7-1B-8bit")
config = load_config("nativ-community/MiniCPM-V-4.7-1B-8bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use nativ-community/MiniCPM-V-4.7-1B-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nativ-community/MiniCPM-V-4.7-1B-8bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nativ-community/MiniCPM-V-4.7-1B-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use nativ-community/MiniCPM-V-4.7-1B-8bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nativ-community/MiniCPM-V-4.7-1B-8bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nativ-community/MiniCPM-V-4.7-1B-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nativ-community/MiniCPM-V-4.7-1B-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nativ-community/MiniCPM-V-4.7-1B-8bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nativ-community/MiniCPM-V-4.7-1B-8bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiniCPM-V-4.7-1B-8bit / validation.json

prince-canuma

Add 8bit MLX conversion of openbmb/MiniCPM-V-4.7-1B (main e928101a)

6ec3a37 verified 4 days ago

Raw History Blame Contribute Delete

1.48 kB

	{
	"status": "passed",
	"checks": [
	"strict checkpoint reload",
	"quantization configuration",
	"text generation",
	"image generation at 16x and 4x downsampling"
	],
	"tests": [
	{
	"case": "text",
	"prompt": "What is 2 + 2? Answer with only the number.",
	"output": "4",
	"elapsed_seconds": 1.36,
	"generation_tokens": 2
	},
	{
	"case": "image_16x",
	"prompt": "Describe the animals and the color of the furniture in this image in one short sentence.",
	"output": "Two tabby cats sleep on a bright pink couch, with remote controls nearby.",
	"elapsed_seconds": 0.735,
	"generation_tokens": 17
	},
	{
	"case": "image_4x",
	"prompt": "Describe the animals in this image in one short sentence.",
	"output": "Two tabby cats sleep on a pink couch, each beside a remote control.",
	"elapsed_seconds": 0.252,
	"generation_tokens": 17
	}
	],
	"quantized_modules": {
	"affine:8:g64": 96
	},
	"A_log_dtypes": {
	"mlx.core.bfloat16": 18
	},
	"image": "https://github.com/Blaizzy/mlx-vlm/blob/e928101a144a3f11a27c7ef8d71b6d889b2d250c/examples/images/cats.jpg",
	"image_sha256": "dea9e7ef97386345f7cff32f9055da4982da5471c48d575146c796ab4563b04e",
	"hardware": "Apple M3 Ultra",
	"software": {
	"mlx": "0.32.3",
	"transformers": "5.19.0",
	"huggingface_hub": "2.2.0"
	},
	"limitations": "Smoke checks only; no benchmark or model-quality evaluation."
	}