This quantization was uploaded on 2026-09-30 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Ling-3.0-tiny-oQ8-fp16
This model was quantized using oQ (oMLX v0.7.0rc1) mixed-precision quantization.
Quantization details
- Model type: bailing_hybrid
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 137
Model size
8B params
Tensor type
U32
路
F16 路
F32 路
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support