Downloads · 30 days
18
19% of all-time downloads
nightmedia/Qwen3-8B-HiveMind-Heretic-qx86-hi-mlx
Qwen3-8B-HiveMind-Heretic-qx86-hi-mlx is a machine learning model from nightmedia. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
0.558,0.757,0.861,0.665,0.420,0.748,0.628
Downloads · 30 days
18
19% of all-time downloads
All-time downloads
95
Public
Parameters
7.7B
7.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors7.1 GB · 100%
How the weights are stored.
U321.5B · 76%
From the Hugging Face model README
0.558,0.757,0.861,0.665,0.420,0.748,0.628
Think of it as a Borg Cube that was taken over by Hugh's crowd, and learned that global warming is a hoax.
It is based on Qwen3-4B, with extra 4B of Brainstorming added by DavidAU
-G
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3-8B-HiveMind-Heretic-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)