Qwen2.5
Collection
The Qwen 2.5 models are a series of AI models trained on 18 trillion tokens, supporting 29 languages and offering advanced features such as instructio • 33 items • Updated • 9
mlx-community/Qwen2.5-7B-Instruct-4bit
The Model mlx-community/Qwen2.5-7B-Instruct-4bit was converted to MLX format from Qwen/Qwen2.5-7B-Instruct using mlx-lm version 0.18.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen2.5-7B-Instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 12,484
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mlx-community/Qwen2.5-7B-Instruct-4bit
Base model
Qwen/Qwen2.5-7B