Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-mlx-oQ8-fp16
This model was quantized using oQ (oMLX v0.3.9.dev2) mixed-precision quantization.
Quantization details
- Model type: mixtral
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 663
Model size
5B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support