Downloads · 30 days
18
16% of all-time downloads
mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-dwq-mmlu-pro-0.73
Qwen3-30B-A3B-Instruct-2507-4bit-dwq-mmlu-pro-0.73 is a machine learning model from mlx-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-dwq-mmlu-pro-0.73 was converted to MLX format from None using mlx-lm version 0.26.2.
Downloads · 30 days
18
16% of all-time downloads
All-time downloads
113
Public
Parameters
30.5B
17.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors17.2 GB · 100%
How the weights are stored.
U323.8B · 80%
From the Hugging Face model README
This model mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-dwq-mmlu-pro-0.73 was converted to MLX format from None using mlx-lm version 0.26.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-dwq-mmlu-pro-0.73")
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)