Ling
Collection
2 items • Updated
Ling-3.0-tiny-oQ6e
This model was quantized using oQ (oMLX v0.6.0rc1) mixed-precision quantization.
Quantization details
- Model type: bailing_hybrid
- Bits: 6
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 597
Model size
8B params
Tensor type
U32
·
BF16 ·
F32 ·
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