Image-Text-to-Text
MLX
Safetensors
English
step3p7
stepfun
step-3.7-flash
vision-language
multimodal
Mixture of Experts
quantized
mxfp4
microscaling
fp4
apple-silicon
text-generation
conversational
custom_code
4-bit precision
Instructions to use osmapi/Step-3.7-Flash-MXFP4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use osmapi/Step-3.7-Flash-MXFP4-mlx 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("osmapi/Step-3.7-Flash-MXFP4-mlx") config = load_config("osmapi/Step-3.7-Flash-MXFP4-mlx") # 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
How to use osmapi/Step-3.7-Flash-MXFP4-mlx with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "osmapi/Step-3.7-Flash-MXFP4-mlx"
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": "osmapi/Step-3.7-Flash-MXFP4-mlx" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use osmapi/Step-3.7-Flash-MXFP4-mlx 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 "osmapi/Step-3.7-Flash-MXFP4-mlx"
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 osmapi/Step-3.7-Flash-MXFP4-mlx
Run Hermes
hermes
Ctrl+K
- 1.56 kB
- 9.22 kB
- 5.72 kB
- 6.91 kB
- 8.38 kB
- 231 kB
- 245 MB xet
- 2.61 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 4.93 GB xet
- 4.95 GB xet
- 2.46 GB xet
- 1.85 GB xet
- 655 MB xet
- 1.21 GB xet
- 174 kB
- 56.8 kB
- 18.7 kB
- 468 Bytes
- 9.98 MB
- 163 kB
- 17.7 kB