Qwen
Collection
6 items • Updated
This quantization was uploaded on 2026-08-28 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Qwen3.8-4B-Distill-MLX-oQ4e-fp16-mtp
This model was quantized using oQ (oMLX v0.6.3) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 51
Model size
4B params
Tensor type
U32
·
F16 ·
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