Qwen3-4B-Thinking-2507-llmc-gptq-calib-ultrachat-200k-train-sft-w4a16-g128-n256-s1024

Base model: Qwen/Qwen3-4B-Thinking-2507

Quantized with llm-compressor.

  • method: gptq
  • weight format: W4A16
  • group size: 128
  • calibration dataset: HuggingFaceH4/ultrachat_200k
  • calibration dataset config: ``
  • calibration split: train_sft
  • calibration samples: 256
  • max sequence length: 1024
Downloads last month
12
Safetensors
Model size
4B params
Tensor type
I64
路
I32
路
BF16
路
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for meteorain/Qwen3-4B-Thinking-2507-llmc-gptq-calib-ultrachat-200k-train-sft-w4a16-g128-n256-s1024

Quantized
(151)
this model