Qwen3.6-27B
Collection
7 items • Updated • 1
This model was converted to MLX format from Qwen/Qwen3.6-27B using oMLX v0.3.6.
Settings
- Level: oQ4
- Sensitivity model: Qwen3.6-27B-MLX-Q8
- Text Only: no
- Non-quant weight dtype: bfloat16
What is "VL"?
"VL" is Vision-Language. See deepsweet/Qwen3.6-27B-MLX-oQ4 for text-only version.
What is "oQ"?
See "oQ: oMLX Universal Dynamic Quantization" for details.
I have M1/M2 Apple Silicon
Consider using specially optimized deepsweet/Qwen3.6-27B-MLX-VL-oQ4-FP16 version with a very noticeable prompt processing boost. See jundot/omlx/issues/604 for details.
Otherwise stick with this one if you have M3+ Apple Silicon.
- Downloads last month
- 39
Model size
5B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for deepsweet/Qwen3.6-27B-MLX-VL-oQ4
Base model
Qwen/Qwen3.6-27B