Edit model card

mlx-community/quantized-gemma-2b

This model was converted to MLX format from google/gemma-2b. 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("mlx-community/quantized-gemma-2b")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
289
Safetensors
Model size
834M params
Tensor type
FP16
·
U32
·
Inference API
This model can be loaded on Inference API (serverless).

Collection including mlx-community/quantized-gemma-2b