ramblingpolymath
/

Qwen3-Coder-30B-A3B-Instruct-W4A16

Text Generation

compressed-tensors

Model card Files Files and versions Community

Qwen3-Coder-30B-A3B-Instruct-W4A16

File size: 167 Bytes

c4b295e

default_stage:
  default_modifiers:
    GPTQModifier:
      targets: [Linear]
      ignore: [lm_head, 're:.*mlp.gate$']
      scheme: W4A16
      dampening_frac: 0.01