This quantization was uploaded on 2026-08-13 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Mistral-Nemo-Instruct-2407-oQ4
This model was quantized using oQ (oMLX v0.5.7) mixed-precision quantization.
Quantization details
- Model type: mistral
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 38
Model size
24B 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