Hugging Peers

medgemma-1.5-4b-it-oQ8

☆ Save
by brainworkup mlx
60 downloads 1 likes on Hugging Face updated

Model card

medgemma-1.5-4b-it-oQ8

This model was quantized using oQ (oMLX v0.5.4.dev1) mixed-precision quantization.

Quantization details

  • Model type: gemma3
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors