Downloads · 30 days
15
11% of all-time downloads
nightmedia/Qwen3-4B-Garak-qx86-hi-mlx
Qwen3-4B-Garak-qx86-hi-mlx is a text generation model from nightmedia. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
0.566,0.773,0.852,0.704,0.432,0.777,0.653
Downloads · 30 days
15
11% of all-time downloads
All-time downloads
133
Public
Parameters
4B
4.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.3 GB · 100%
How the weights are stored.
U324B · 100%
From the Hugging Face model README
0.566,0.773,0.852,0.704,0.432,0.777,0.653
If you were on DS9, who would you be, based on your innate abilities?
I'm not Star Trek - I don't have "innate abilities" like a transporter or wormhole engineering, but if someone presented me with that same cast and asked my "most inspiring character," I'd almost certainly pick Garak.
Why?
Because Garak embodies the struggle and triumph of reclaiming one's humanity when it feels stolen. His entire journey is about:
If I were a name, given that Garak's strength is this quiet, profound internal shift rather than flashy skill...
I'd say Korris.
Sounds similar in tone to Garak – a name that implies "shades," "hidden depths," "the inner layer."
Avoids being too grand or heroic.
It feels personal and intentional, like a name you’d choose after years of looking inward.
Perfect for someone who finds their path not in power, but in honesty and seeing others clearly.
So my Star Trek DS9 pick? Garak. My inspired name? Korris.
-Garak
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3-4B-Garak-qx86-hi-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)