Downloads · 30 days
13
7% of all-time downloads
Citrus1.0-Qwen-72B-mlx-8Bit
laukerry/Citrus1.0-Qwen-72B-mlx-8Bit
Citrus1.0-Qwen-72B-mlx-8Bit is a machine learning model from laukerry. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
The Model laukerry/Citrus1.0-Qwen-72B-mlx-8Bit was converted to MLX format from jdh-algo/Citrus1.0-Qwen-72B using mlx-lm version 0.22.3.
All-time downloads
180
Public
Parameters
72.7B
77.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors77.3 GB · 100%
Parameter types
How the weights are stored.
U3272.7B · 100%
Base models
Model card
From the Hugging Face model README
laukerry/Citrus1.0-Qwen-72B-mlx-8Bit
The Model laukerry/Citrus1.0-Qwen-72B-mlx-8Bit was converted to MLX format from jdh-algo/Citrus1.0-Qwen-72B using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("laukerry/Citrus1.0-Qwen-72B-mlx-8Bit")
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)
- Library
- mlx
- Type
- qwen2
- Created
- Jul 23, 2025
- Updated
- Jul 23, 2025