Instructions to use krzonkalla/test-quant-mlx-rio-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use krzonkalla/test-quant-mlx-rio-mini 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("krzonkalla/test-quant-mlx-rio-mini") config = load_config("krzonkalla/test-quant-mlx-rio-mini") # 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
- LM Studio
- Pi new
How to use krzonkalla/test-quant-mlx-rio-mini with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "krzonkalla/test-quant-mlx-rio-mini"
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": "krzonkalla/test-quant-mlx-rio-mini" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use krzonkalla/test-quant-mlx-rio-mini 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 "krzonkalla/test-quant-mlx-rio-mini"
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 krzonkalla/test-quant-mlx-rio-mini
Run Hermes
hermes
Python
from mlx_vlm import load, generate
model, processor = load("krzonkalla/test-quant-mlx-rio-mini")
# Apenas texto
output = generate(
model,
processor,
prompt="Me explique brevemente a Teoria da Relatividade Geral.",
max_tokens=64000,
)
print(output)
# Com imagens
output = generate(
model,
processor,
prompt="Me diga o que há nessa imagem.",
image="path/to/image.png",
max_tokens=64000,
)
print(output)
Nota
O processador de vídeo do Qwen3.5 depende do torchvision. Para uso só com imagens, o mlx-vlm funciona sem o PyTorch. Para habilitar suporte a vídeo, instale o torch e o torchvision.
- Downloads last month
- 12
Model size
5B params
Tensor type
BF16
·
U32 ·
F32 ·
Hardware compatibility
Log In to add your hardware
3-bit