Downloads · 30 days
204
22% of all-time downloads
vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16 is a image-text-to-text model from vadimayegorov. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
The Model vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed26-mlx-fp16 was converted to MLX format from zecanard/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinki…
Downloads · 30 days
204
22% of all-time downloads
All-time downloads
916
Public
Parameters
39.1B
15.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.7 GB · 100%
How the weights are stored.
U3239.1B · 100%
From the Hugging Face model README
The Model vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16 was converted to MLX format from zecanard/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6 using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16")
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)