MedGemma-4B-IT — MLX 4-bit

Converted from google/medgemma-4b-it for Apple MLX.

Usage

python -m mlx_vlm.generate \
  --model YOUR_USERNAME/medgemma-4b-it-mlx-4bit \
  --prompt "Describe this image." \
  --image path/to.jpg \
  --max-tokens 128

Downloads last month: 10

Safetensors

Model size

0.9B params

Tensor type

BF16

U32

MLX

Hardware compatibility

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for arkaprovob/medgemma-4b-it-mlx-4bit

Base model

google/gemma-3-4b-pt

Finetuned

google/medgemma-4b-pt

Finetuned

google/medgemma-4b-it

Finetuned

(626)

this model