Support GPTQ for LLMs INT4 quantization
Open
@hitarthmehta is already working on this.
Since May 26, 2026.
question
- Dominant language
- Python
- Stars
- 2.7k
- Forks
- 464
- PR merge metrics
- No merged PRs in 30d
Description
I am trying to quantize Qwen3-VL (a multimodal LLM) to INT4 using AIMET. Due to the hardware (Snapdragon 8295), I can only use per‑channel quantization. I first tried basic PTQ, but the accuracy was insufficient. Then I used SpinQuant, which improved accuracy, but it is still not enough. I read the SpinQuant paper, which states that after applying the rotation, GPTQ is used for quantization. However, AIMET's implementation does not seem to follow this approach.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.