mlx-community/Qwen2-72B-Instruct-4bit
The Model mlx-community/Qwen2-72B-Instruct-4bit was converted to MLX format from Qwen/Qwen2-72B-Instruct using mlx-lm version 0.14.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen2-72B-Instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 52
Inference API (serverless) does not yet support mlx models for this pipeline type.