Qwen3.6 MTP OQE FP16
Collection
8 items • Updated
Text and vision retained
Quantised using oMLX v0.5.0.rc1 OQ Enhanced quantization (oQe) iMatrix
MTP Heads retained
FP16 is fastest on M1/M2 , but this can work on all MLX inferencing systems
This model is using the LATEST FROGGERIC chat template upgrade (Fixed jinja chat templates for Qwen 3.5 & 3.6 (v21))
- Downloads last month
- 50
Model size
28B params
Tensor type
U32
·
F32 ·
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
Model tree for wezzel98765/Qwen3.6-27B-oQ4e-fp16-mtp
Base model
Qwen/Qwen3.6-27B