Instructions to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit 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("Jackrong/MLX-Qwopus3.5-9B-v3-4bit") 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
- Unsloth Studio
How to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jackrong/MLX-Qwopus3.5-9B-v3-4bit to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jackrong/MLX-Qwopus3.5-9B-v3-4bit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Jackrong/MLX-Qwopus3.5-9B-v3-4bit to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Jackrong/MLX-Qwopus3.5-9B-v3-4bit", max_seq_length=2048, ) - Pi
How to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Jackrong/MLX-Qwopus3.5-9B-v3-4bit"
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": "Jackrong/MLX-Qwopus3.5-9B-v3-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit 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 "Jackrong/MLX-Qwopus3.5-9B-v3-4bit"
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 Jackrong/MLX-Qwopus3.5-9B-v3-4bit
Run Hermes
hermes
- MLX LM
How to use Jackrong/MLX-Qwopus3.5-9B-v3-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Jackrong/MLX-Qwopus3.5-9B-v3-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Jackrong/MLX-Qwopus3.5-9B-v3-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jackrong/MLX-Qwopus3.5-9B-v3-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
Vision Support?
Apologies for the noob question, but does this model then also support vision?
From my understanding, the vision should be basically inside of the model file, but LM Studio doesn't recognise this as a vision model.
Hi there! No worries at all—everyone starts somewhere 😊
Happy to clarify this for you. The issue you’re encountering is likely due to the current limitations in the MLX environment, where the vision projection layer may not be properly loaded.
As mentioned earlier, LM Studio requires the mmproj file to enable vision support. This file is not included in the default model package.
You can try the following:
• Look for the file named mmproj-BF16.gguf in the repository
• Place it in the same folder as your model
• Then reload the model in LM Studio
Alternatively, using the GGUF format with the correct mmproj file should allow LM Studio to properly recognize the model as a vision-capable (multimodal) model.