This quantization was uploaded on 2026-07-24 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Ornith-1.0-35B-AEON-Ultimate-Uncensored-oQ6e
This model was quantized using oQ (oMLX v0.5.3) mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 6
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 305
Model size
8B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for swdjojo/Ornith-1.0-35B-AEON-Ultimate-Uncensored-oQ6e
Base model
deepreinforce-ai/Ornith-1.0-35B