Instructions to use MCES10-Software/cpp-qwen3-4B-Instruct-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MCES10-Software/cpp-qwen3-4B-Instruct-2507 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("MCES10-Software/cpp-qwen3-4B-Instruct-2507")

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)

Inference
Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use MCES10-Software/cpp-qwen3-4B-Instruct-2507 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "MCES10-Software/cpp-qwen3-4B-Instruct-2507"

Configure 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": "MCES10-Software/cpp-qwen3-4B-Instruct-2507"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MCES10-Software/cpp-qwen3-4B-Instruct-2507 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 "MCES10-Software/cpp-qwen3-4B-Instruct-2507"

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 MCES10-Software/cpp-qwen3-4B-Instruct-2507

Run Hermes

hermes

MLX LM

How to use MCES10-Software/cpp-qwen3-4B-Instruct-2507 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "MCES10-Software/cpp-qwen3-4B-Instruct-2507"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "MCES10-Software/cpp-qwen3-4B-Instruct-2507"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "MCES10-Software/cpp-qwen3-4B-Instruct-2507",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CPP-qwen3-4B-Instruct-2507

Features

This model is based on qwen3-4B-Instruct-2507
Fine Tuned on MCES10-Software/CPP-Code-Solutions Dataset
4 Billion Parameters
Finetuned with MLX
model.safetensors

Benchmark

MAX TOKENS = 500 Apple Silicon Macbook Pro 18,3 M1 PRO 16 GB RAM

Write a function that checks if a number is prime.

bool isPrime(int n) {
    if (n <= 1) return false;
    for (int i = 2; i * i <= n; ++i) {
        if (n % i == 0) return false;
    }
    return true;
}

49.27 tok/sec 63 tokens 0.24s to first token Credits

MCES10 Software

Thanks to:

QWEN for the model

Downloads last month: 18

Safetensors

Model size

4B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for MCES10-Software/cpp-qwen3-4B-Instruct-2507

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1703)

this model

Quantizations

1 model

MCES10-Software
/

cpp-qwen3-4B-Instruct-2507

CPP-qwen3-4B-Instruct-2507

Features

Benchmark

Model tree for MCES10-Software/cpp-qwen3-4B-Instruct-2507

Dataset used to train MCES10-Software/cpp-qwen3-4B-Instruct-2507