This quantization was uploaded on 2026-07-12 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Qwythos-9B-v2-MLX-oQ4
This model was quantized using oQ (oMLX v0.5.0) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 468
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