mlx-community/Qwen3.5-397B-A17B-8bit-gs32

This model mlx-community/Qwen3.5-397B-A17B-8bit-gs32 was converted to MLX format from Qwen/Qwen3.5-397B-A17B using mlx-lm version 0.30.8.

NOTE: This is a text-only version instead of the full multimodal experience.

Recipe:

  • 8-bit
  • group-size 32
  • 9 bits per weight (bpw)
Downloads last month
1,071
Safetensors
Model size
396B params
Tensor type
BF16
U32
F32
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for mlx-community/Qwen3.5-397B-A17B-8bit-gs32

Quantized
(17)
this model