This quantization was uploaded on 2026-08-21 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Qwen3.5-0.8B-oQ4e-mtp
This model was quantized using oQ (oMLX v0.6.3rc2) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 7
Model size
0.1B params
Tensor type
BF16
路
U32 路
F32 路
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support