GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Paper
•
2210.17323
•
Published
•
10
4-bit GPTQ quantized version of Qwen3-4B-Instruct-2507 for use with the Private LLM app. This model has been abilterated for slop reduction using heretic.
- Downloads last month
- -
Model tree for numen-tech/Qwen3-4B-Instruct-2507-heretic-noslop-GPTQ-Int4
Base model
Qwen/Qwen3-4B-Instruct-2507