Working in Progress!

This model is a version of hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled converted via MLX 0.31.2

I do not recommend its use for practical applications as I have not yet completed testing on quantization for now.

Downloads last month
1,037
Safetensors
Model size
35B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

5-bit

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

Model tree for nabi-chan/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-MLX-5bit

Collection including nabi-chan/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-MLX-5bit