Instructions to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"

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": "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit 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 "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"

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 pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit"

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 "pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit" \
  --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-4.7-35B-A3B for mlx-serve (4-bit)

An MLX affine quantization of openbmb/MiniCPM-V-4.7-35B-A3B, distributed under the base model's Apache-2.0 license.

Text-only pack

This pack contains language model weights only. It does not support image or video inputs and does not include the MiniCPM vision tower or merger. Its native root model type is minicpmv4_7, and it requires mlx-serve v26.10.2 or later.

Quantization

Affine 4-bit quantization, group size 64. Routed MoE experts are 4-bit; per-layer router gates and shared-expert gates are 8-bit. Norms, scales, and biases remain BF16.

Setup

mlx-serve serve --model pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit

Benchmark

Standard suite on Apple M4 Max with mlx-serve 26.10.2:

Benchmark	Result
MMLU-Pro (400 questions)	89.75% (359/400)
GSM8K (50 questions)	100%
Coding (6 tasks)	6/6
Decode	60.6 tok/s
Prefill	343 tok/s
Peak memory	24.7 GB

MMLU-Pro is public, so training contamination cannot be ruled out.

Attribution

MiniCPM-V 4.7 was created by OpenBMB. This is an independent MLX conversion for mlx-serve.

Disclaimer

This is an unofficial, text-only conversion. Validate it for your workload before production use.

Downloads last month: 1,105

Safetensors

Model size

35B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for pgmharikrishnan/MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bit

Base model

openbmb/MiniCPM-V-4.7-35B-A3B

Quantized

(54)

this model