mlx-community/Qwen2.5-32B-Instruct-8bit

The Model mlx-community/Qwen2.5-32B-Instruct-8bit was converted to MLX format from Qwen/Qwen2.5-32B-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/Qwen2.5-32B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 96

Safetensors

Model size

9.22B params

Tensor type

FP16

U32

Inference Examples

Text Generation

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

Model tree for mlx-community/Qwen2.5-32B-Instruct-8bit

Base model

Qwen/Qwen2.5-32B

Finetuned

(14)

this model

Collection including mlx-community/Qwen2.5-32B-Instruct-8bit

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 • 5