Converted from Qwen/Qwen3.5-27B using mlx_lm.convert with --q-mode nvfp4 --q-group-size 16 on 2026-03-05, 23:32.

Downloads last month
107
Safetensors
Model size
7B params
Tensor type
U8
U32
BF16
F32
MLX
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

Model tree for dumtjul/Qwen3.5-27B-mlx-nvfp4

Base model

Qwen/Qwen3.5-27B
Quantized
(197)
this model