Downloads · 30 days
31
9% of all-time downloads
DeepSeek-R1-Distill-Qwen-32B-MLX-4bits
moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits
DeepSeek-R1-Distill-Qwen-32B-MLX-4bits is a text generation model from moot20. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The Model moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.21.1.
All-time downloads
337
Public
Parameters
32.8B
18.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18.4 GB · 100%
Parameter types
How the weights are stored.
U3232.8B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits
The Model moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.21.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("moot20/DeepSeek-R1-Distill-Qwen-32B-MLX-4bits")
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
- transformers
- Type
- qwen2
- License
- mit
- Created
- Feb 3, 2025
- Updated
- Feb 3, 2025