Downloads · 30 days
27
22% of all-time downloads
Qwen3-4B-Instruct-2507-4bit
decompute/Qwen3-4B-Instruct-2507-4bit
Qwen3-4B-Instruct-2507-4bit is a text generation model from decompute. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This model mlx-community/Qwen3-4B-Instruct-2507-4bit was converted to MLX format from Qwen/Qwen3-4B-Instruct-2507 using mlx-lm version 0.26.2.
All-time downloads
121
Public
Parameters
4B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
Parameter types
How the weights are stored.
U324B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
mlx-community/Qwen3-4B-Instruct-2507-4bit
This model mlx-community/Qwen3-4B-Instruct-2507-4bit was converted to MLX format from Qwen/Qwen3-4B-Instruct-2507 using mlx-lm version 0.26.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen3-4B-Instruct-2507-4bit")
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
- qwen3
- License
- apache-2.0
- Created
- Oct 23, 2025
- Updated
- Oct 23, 2025