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)