Hugging Face's logo

root4k
/
Qwen3-30B-A3B-Thinking-2507-mlx-mxfp4

Text Generation
MLX
Safetensors
qwen3_moe
conversational
4-bit precision
Model card Files
xet
Community
README.md exists but content is empty.
Downloads last month
-
Safetensors
Model size
31B params
Tensor type
U8
·
U32
·
BF16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for root4k/Qwen3-30B-A3B-Thinking-2507-mlx-mxfp4

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507
Quantized
(72)
this model

Collection including root4k/Qwen3-30B-A3B-Thinking-2507-mlx-mxfp4