mlx-community/Qwen2.5-14B-Instruct-3bit

The Model mlx-community/Qwen2.5-14B-Instruct-3bit was converted to MLX format from Qwen/Qwen2.5-14B-Instruct using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-14B-Instruct-3bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 40

Safetensors

Model size

1.85B 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/Qwen2.5-14B-Instruct-3bit

Base model

Qwen/Qwen2.5-14B

Quantized

(54)

this model