Downloads · 30 days
28
12% of all-time downloads
Magistry-24B-v1.0-mlx-8Bit
McG-221/Magistry-24B-v1.0-mlx-8Bit
Magistry-24B-v1.0-mlx-8Bit is a machine learning model from McG-221. 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 card lists the license as apache-2.0.
The Model McG-221/Magistry-24B-v1.0-mlx-8Bit was converted to MLX format from sophosympatheia/Magistry-24B-v1.0 using mlx-lm version 0.29.1.
All-time downloads
229
Public
Parameters
23.6B
25.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors25 GB · 100%
Parameter types
How the weights are stored.
U3223.6B · 100%
Base models
Model card
From the Hugging Face model README
McG-221/Magistry-24B-v1.0-mlx-8Bit
The Model McG-221/Magistry-24B-v1.0-mlx-8Bit was converted to MLX format from sophosympatheia/Magistry-24B-v1.0 using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("McG-221/Magistry-24B-v1.0-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
- mistral
- License
- apache-2.0
- Languages
- en
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026