Downloads · 30 days
73
3% of all-time downloads
DeepSeek-V3.2-MLX-4bit
sjug/DeepSeek-V3.2-MLX-4bit
DeepSeek-V3.2-MLX-4bit is a text generation model from sjug. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
This model sjug/DeepSeek-V3.2-MLX-4bit was converted to MLX format from deepseek-ai/DeepSeek-V3.2 using mlx-lm version 0.28.4.
All-time downloads
2.6K
Public
Parameters
672B
378 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 GB · 100%
Parameter types
How the weights are stored.
U32672B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
sjug/DeepSeek-V3.2-MLX-4bit
This model sjug/DeepSeek-V3.2-MLX-4bit was converted to MLX format from deepseek-ai/DeepSeek-V3.2 using mlx-lm version 0.28.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sjug/DeepSeek-V3.2-MLX-4bit")
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)
- Task
- Text Generation
- Library
- mlx
- Type
- deepseek_v32
- License
- mit
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025