This quantization was uploaded on 2026-09-10 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
gemma-4-12B-it-oQ4e
This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.
Quantization details
- Model type: gemma4_unified
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 30
Model size
12B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download TiGa-RCE/gemma-4-12B-it-oQ4e --local-dir gemma-4-12B-it-oQ4e