Edit model card

madroid/qwen1.5-0.5B-4bit-flow

This model was converted to MLX format from mlx-community/Qwen1.5-0.5B-Chat-4bit. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("madroid/qwen1.5-0.5B-4bit-flow")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
6
Safetensors
Model size
228M params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.