anthonymikinka

/

Qwen3-0.6B-w_uint4_per_group_asym-awq

like 0

When I try to run the normal ONNX community models on Runtime GenAI - it throws weird errors. Only Llama models were working, except that nothing worked. Tried Gemma3, Qwen3 and now your model as well. Can you please help me on how are inferencing this model.

@anthonymikinka

Sorry for the late reply, paste your error and lmk I can look into an issue. Note that to run the Model and to Convert the model, I believe I used different conda environments. If I am remembering correctly.

Hello! I am a Computer Science student preparing my first arXiv submission in cs.AI. Since this is my first submission, arXiv requires an endorsement from someone who has previously submitted to arXiv under cs.AI.

If you have submitted to cs.AI before and are willing to help, I would sincerely appreciate it if you could endorse me via the link below:

https://arxiv.org/auth/endorse?x=TPGSX3

Thank you very much for your time and consideration.

Hello! I am a Computer Science student preparing my first arXiv submission in cs.AI. Since this is my first submission, arXiv requires an endorsement from someone who has previously submitted to arXiv under cs.AI.

If you have submitted to cs.AI before and are willing to help, I would sincerely appreciate it if you could endorse me via the link below:

https://arxiv.org/auth/endorse?x=TPGSX3

Thank you very much for your time and consideration.

If you are a university student, you should signup to arXiv with your edu email. I did this and was able to submit my paper to Queue without an endorsement. I did see my preprint go through, I think it was 'verification' or something like that. I don't know if thats for everyone, figured it may be for me explicitly because I'm a uni student first time posting. Oh if I were you, I'd make a ORCID too with your EDU email and link those two platforms!