[OpenVINO] Support Qwen3-next

[rkazants]

What does this PR do?

Example of conversion cmd-line for Qwen/Qwen3-Next-80B-A3B-Instruct:

optimum-cli export openvino -m Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct

Example of inference for Qwen/Qwen3-Next-80B-A3B-Instruct using OpenVINO backend:

from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_path = "./Qwen3-Next-80B-A3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = OVModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)

# change input text as desired
input_text = "The capital of France is"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt")
# generate output tokens
output = model.generate(**input_tokens, max_length=10)
# decode output tokens into text
output = tokenizer.batch_decode(output)
print(output[0])

Before submitting

• [N/A] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[Copilot]

Pull request overview

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[IlyasMoutawwakil]

LGTM !

[MaximProshin]

FYI After fixes in OV for group-wise quantization, I was able to measure the accuracy for default int4 and I got (CPU, WWB Similarity): 0.960114

[savvadesogle]

Thank you 🙏

[savvadesogle]

Hello, Roman. @rkazants

Can we convert models from the Intel repository to OpenVINO? AutoRound models.
And how to do in properly

https://huggingface.co/Intel/Qwen3-Coder-Next-int4-AutoRound

[rkazants]

optimum-cli export openvino -m Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct

Hi @savvadesogle,

Can you try this command for conversion:

optimum-cli export openvino -m Intel/Qwen3-Coder-Next-int4-AutoRound Qwen3-Coder-Next-int4-AutoRound

@ljaljushkin, @MaximProshin, @mvafin, did you see any problems for converting this quantized model from NNCF perspective or PyTorch FE?

Best regards,
Roman