Downloads · 30 days
93
9% of all-time downloads
cs2764/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32
Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32 is a text generation model from cs2764. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model cs2764/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32 was converted to MLX format from huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated using mlx-lm version 0.26.2.
Downloads · 30 days
93
9% of all-time downloads
All-time downloads
987
Public
Parameters
30.5B
26.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors26.7 GB · 100%
How the weights are stored.
U3230.5B · 100%
From the Hugging Face model README
The Model cs2764/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32 was converted to MLX format from huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated using mlx-lm version 0.26.2.
This model was converted with the following quantization settings:
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cs2764/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32")
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)