Downloads · 30 days
70
3% of all-time downloads
DeepSeek-V3.2_dq4-mlx
cs2764/DeepSeek-V3.2_dq4-mlx
DeepSeek-V3.2_dq4-mlx is a text generation model from cs2764. Use it when you need the model to write or continue text. It is set up for mlx.
This model is a DQ4 quantized version of the original model DeepSeek-V3.2. It was quantized locally using the mlxlm library.
All-time downloads
2.5K
Public
Parameters
672B
394 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors394 GB · 100%
Parameter types
How the weights are stored.
U32672B · 100%
Try a prompt
Model card
From the Hugging Face model README
DeepSeek-V3.2_dq4
This model is a DQ4 quantized version of the original model [DeepSeek-V3.2](Local Model).
It was quantized locally using the mlx_lm library.
Quantization Methodology (DQ4)
This model was quantized using the dynamic DQ4 (4-bit / 5-bit / 6-bit / 8-bit mixed) approach, inspired by the methodology described in the mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8 repository.
The weights are mixed based on MLX layers:
- Expert layers (switch_mlp / mlp) are quantized to 4-bit.
- The first 5 layers are kept at higher quality (6-bit).
- Every 5th layer is medium quality (5-bit).
- All other layers (e.g. attention, normalization) remain at 8-bit to serve as the "8-bit brain".
- Task
- Text Generation
- Library
- mlx
- Type
- deepseek_v32
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026