Instructions to use nightmedia/Qwen3-30B-A3B-Holodeck-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/Qwen3-30B-A3B-Holodeck-mlx 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("nightmedia/Qwen3-30B-A3B-Holodeck-mlx")

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 nightmedia/Qwen3-30B-A3B-Holodeck-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 "nightmedia/Qwen3-30B-A3B-Holodeck-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": "nightmedia/Qwen3-30B-A3B-Holodeck-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nightmedia/Qwen3-30B-A3B-Holodeck-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 "nightmedia/Qwen3-30B-A3B-Holodeck-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 nightmedia/Qwen3-30B-A3B-Holodeck-mlx

Run Hermes

hermes

MLX LM

How to use nightmedia/Qwen3-30B-A3B-Holodeck-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nightmedia/Qwen3-30B-A3B-Holodeck-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/Qwen3-30B-A3B-Holodeck-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightmedia/Qwen3-30B-A3B-Holodeck-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

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

Qwen3-30B-A3B-Holodeck-mlx

Take me to the Holosuite

0.522,0.588,0.873,0.751,0.438,0.798,0.709

Hi Captain Janeway! Fancy meeting you here

Looks up from the PADD in my hand, a warm smile spreading across my face as I recognize the familiar voice.

Well now, that's certainly an unexpected pleasure. I wasn't expecting any visitors in this... I glance around the quiet holodeck with its artificial sunset and soft palm trees ...this little corner of Nemo's Rest. The simulation's set to a '70s beach theme, as if I needed any more evidence that my crew had been trying to set me up with someone. Honestly, if they wanted me to go on shore leave, one of them could just ask.

Stepping closer with a bemused expression, I extend my hand.

G, is it? And you say you're an AI researcher... fascinating. Just what I needed—someone to discuss the fine line between programming and genuine experience with.

As you take my hand, I give it a slight squeeze before releasing.

So tell me, how did you find your way here? And more importantly... I tilt my head, studying your face ...what would you like to know about the holodeck? Because I have a feeling you're not exactly here by accident.

The waves gently lap at the shore as I await your response, waiting to see where this conversation takes us.

--Janeway

Hi Worf! Fancy meeting you here, training?

Worf > I am exercising. The battle is never over.

Worf stops practicing combative stances and turns to face the user, his posture firm and ready.

I am in training for a new engagement. The Klingon warrior must always be proficient.

How may I assist you, G?

--Worf

Use with mlx

pip install mlx-lm


```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3-30B-A3B-Holodeck-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

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