mlx-community/Qwen2.5-14B-4bit

The Model mlx-community/Qwen2.5-14B-4bit was converted to MLX format from Qwen/Qwen2.5-14B 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/Qwen2.5-14B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 24

Safetensors

Model size

2.31B params

Tensor type

FP16

U32

Inference Examples

Text Generation

Inference API (serverless) does not yet support mlx models for this pipeline type.

Collection including mlx-community/Qwen2.5-14B-4bit

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 Oct 12 • 6