[Docs] Add Qwen3.5 to Key Models

[dsikka]

SUMMARY:

• Example walkthrough
• Notes about transformers version
• Should land https://github.com/vllm-project/llm-compressor/pulls/dsikka to make these examples make sense

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly expands the documentation by integrating the Qwen3.5 model family into the key models section. It provides practical, step-by-step examples for quantizing both the sparse MoE and vision-language variants of Qwen3.5, enabling users to efficiently apply advanced quantization techniques. The addition of these examples aims to improve usability and demonstrate compatibility with recent transformers library versions.

Highlights

• New Model Documentation: Added comprehensive documentation for the Qwen3.5 family of models, including an overview page and specific quantization examples.
• Qwen3.5 MoE Quantization Example: Included a detailed walkthrough for quantizing the Qwen3.5-122B-A10B sparse MoE model to NVFP4 using calibration data, emphasizing expert calibration.
• Qwen3.5 Vision-Language Quantization Example: Provided an example for quantizing the Qwen3.5-27B vision-language model to NVFP4A16 using data-free PTQ, including a sample generation step.
• Transformers Version Requirement: Noted that these examples require transformers >= v5 and provided installation instructions.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces new documentation and examples for quantizing Qwen3.5 models, including a sparse MoE variant (NVFP4) and a vision-language model (NVFP4A16). The review suggests using pip for installing transformers for broader compatibility, consolidating regex patterns in the quantization ignore list for better clarity, and explicitly setting save_compressed=True when saving the quantized model for consistency.

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[brian-dellabetta]

I agree with the gemini comment on the visual ignore regexes, otherwise LGTM

[dsikka]

@claude review

[dsikka]

@claude hello - update this PR