Downloads · 30 days
149
6% of all-time downloads
Qwen3.6-35B-A3B-DFlash-MLX-6bit
funnygeeker/Qwen3.6-35B-A3B-DFlash-MLX-6bit
Qwen3.6-35B-A3B-DFlash-MLX-6bit is a text generation model from funnygeeker. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This model was converted to MLX format from z-lab/Qwen3.6-35B-A3B-DFlash.
All-time downloads
2.5K
Public
Parameters
386M
338 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors338 MB · 100%
Parameter types
How the weights are stored.
U32386M · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
This model was converted to MLX format from z-lab/Qwen3.6-35B-A3B-DFlash.
Code To Quantify This Model
from mlx_vlm import convert
convert(
hf_path="/Volumes/original_model_path/Qwen3.6-35B-A3B-DFlash",
mlx_path="/Volumes/quantized_model_path/Qwen3.6-35B-A3B-DFlash-MLX-6bit",
quantize=True,
q_bits=6,
q_group_size=32
)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026