Downloads · 30 days
49
3% of all-time downloads
porschefreak/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3Bit
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3Bit is a text generation model from porschefreak. 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.
The Model porschefreak/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3Bit was converted to MLX format from mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit…
Downloads · 30 days
49
3% of all-time downloads
All-time downloads
1.8K
Public
Parameters
39.1B
41.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors41.5 GB · 100%
How the weights are stored.
U3239.1B · 100%
From the Hugging Face model README
The Model porschefreak/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3Bit was converted to MLX format from mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("porschefreak/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)