chore(model gallery): Update changed SHA256 checksums for Qwen 3.5 models (+replace unavailable 35B A3B quant.)

[rampa3]

Description

This PR fixes invalid SHA256 checksums for updated Qwen 3.5 models and derivatives, and replaces currently non-existing Qwen3.5-35B-A3B-UD-Q4_K_M quantization with Qwen3.5-35B-A3B-UD-Q4_K_L (as nearest replacement) for Qwen 3.5 35B A3B model.

Notes for Reviewers

PR is being submitted as draft due to need of testing for updated models. Smaller models I can test by myself over time, but I am looking for help with big size ones, as I cannot run those on my hardware. Help with testing smaller models is welcome too, as I am busy currently, and won't be able to test all the smaller ones too quickly due to that.

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	9d70649
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/69b03a0564bbf80008c38c10
😎 Deploy Preview	https://deploy-preview-8938--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[mudler]

Thank you!

[rampa3]

@mudler Wasn't able to get any testers for the big models that I cannot test with my HW configuration for quite a some time now. Asking in #model-gallery on LocalAI Discord did not yielded any reaction. Should I test the updated SHAs for the smaller models when I have a moment, fix conflicts, and mark it as ready without the bigger size ones to not just let the PR rot?

[mudler]

hey @rampa3 I think this PR now has been superseeded by the the automated bot. On a daily basis it checks against models for checksum mismatch

[rampa3]

hey @rampa3 I think this PR now has been superseeded by the the automated bot. On a daily basis it checks against models for checksum mismatch

Ok, closing it then. Thanks for reply!