cyankiwi
/

Qwen3-Coder-Next-AWQ-4bit

Text Generation

compressed-tensors

Model card Files Files and versions

Resources

View closed (1)

120 TPS on sglang - very nice indeed

#7 opened about 1 month ago by

win10/SVD-Qwen3-Coder-Next-Thinking

#6 opened about 2 months ago by

Feel almost bad for asking this, but do you plan an 8bit version too?

#4 opened about 2 months ago by

Can we perform 4-bit quantization for the awq of the Step-3.5-Flash model? The VLLM can run it.

#3 opened about 2 months ago by

模型量化的效果并不理想

#2 opened about 2 months ago by

how to fix: KeyError: 'model.layers.30.mlp.shared_expert.gate_gate_up_proj.weight'

#1 opened about 2 months ago by