mlx-community/Qwen2-7B-Instruct-8bit

The Model mlx-community/Qwen2-7B-Instruct-8bit was converted to MLX format from Qwen/Qwen2-7B-Instruct using mlx-lm version 0.14.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2-7B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
126
Safetensors
Model size
2.14B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support